{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:07:33Z","timestamp":1781107653049,"version":"3.54.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,8]]},"DOI":"10.1109\/noms56928.2023.10154210","type":"proceedings-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T12:50:45Z","timestamp":1687524645000},"page":"1-10","source":"Crossref","is-referenced-by-count":6,"title":["MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks"],"prefix":"10.1109","author":[{"given":"Raffaele","family":"Galliera","sequence":"first","affiliation":[{"name":"Florida Institute for Human & Machine Cognition (IHMC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Morelli","sequence":"additional","affiliation":[{"name":"Florida Institute for Human & Machine Cognition (IHMC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Fronteddu","sequence":"additional","affiliation":[{"name":"Florida Institute for Human & Machine Cognition (IHMC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niranjan","family":"Suri","sequence":"additional","affiliation":[{"name":"Florida Institute for Human & Machine Cognition (IHMC)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s21134510"},{"key":"ref2","article-title":"Fairness of Congestion-Based Congestion Control: Experimental Evaluation and Analysis","author":"Ma","year":"2017","journal-title":"arXiv: Networking and Internet Architecture"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/65.923938"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.09.025"},{"key":"ref5","volume-title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","author":"Rudin","year":"2021"},{"issue":"1","key":"ref6","first-page":"3","article-title":"Learning dexterous in-hand manipulation","volume":"39","year":"2020","journal-title":"OpenAI: Marcin Andrychowicz"},{"key":"ref7","volume-title":"Soft Actor-Critic Algorithms and Applications","author":"Haarnoja","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5220\/0010516000170028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.011.2000603"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108033"},{"key":"ref11","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"Haarnoja","year":"2018","journal-title":"CoRR abs\/1801.01290"},{"key":"ref12","article-title":"Time Limits in Reinforcement Learning","author":"Pardo","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref14","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icccn49398.2020.9209750"},{"key":"ref16","article-title":"MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions","author":"Sivakumar","year":"2019"},{"key":"ref17","article-title":"Park: An Open Platform for Learning-Augmented Computer Systems","volume":"32","author":"Mao","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","volume-title":"Ubiquiti-EdgeOS"},{"key":"ref19","article-title":"Naval Research Laboratory (NRL) PROTocol Engineering Advanced Networking (PROTEAN) Research Group","year":"2021","journal-title":"Multi-Generator (MGEN) Network Test Tool"},{"key":"ref20","volume-title":"RL Baselines3 Zoo","author":"Raffin"},{"issue":"268","key":"ref21","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Paszke"},{"key":"ref23","volume-title":"OpenAI Gym","author":"Brockman","year":"2016"},{"key":"ref24","first-page":"3050","article-title":"A Deep Reinforcement Learning Perspective on Internet Congestion Control","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Jay"},{"key":"ref25","volume-title":"QUIC: A UDP-Based Multiplexed and Secure Transport. RFC 9000. IETF","author":"Jana Iyengar","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/milcom.2010.5680364"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/milcom47813.2019.9021047"},{"key":"ref28","volume-title":"The NewReno Modification to TCP\u2019s Fast Recovery Algorithm","author":"Gurtov","year":"2012"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/190809.190317"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3009824"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ifipnetworking55013.2022.9829781"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/sisy.2013.6662595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icdcs51616.2021.00094"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/elinfocom.2019.8706382"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/icdm.2004.10063"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/jsacocn.2008.033508"},{"key":"ref38","first-page":"395","article-title":"PCC: Re-Architecting Congestion Control for Consistent High Performance","volume-title":"Proceedings of the 12th USENIX Conference on Networked Systems Design and Implementation","author":"Dong"},{"key":"ref39","first-page":"731","article-title":"Pantheon: the training ground for Internet congestion-control research","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Yan"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref41","article-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih","year":"2013","journal-title":"CoRR abs\/1312.5602"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2019.2904358"},{"key":"ref43","first-page":"3050","article-title":"A Deep Reinforcement Learning Perspective on Internet Congestion Control","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Jay"},{"key":"ref44","article-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","author":"Espeholt","year":"2018","journal-title":"CoRR abs\/1802.01561"}],"event":{"name":"NOMS 2023-2023 IEEE\/IFIP Network Operations and Management Symposium","location":"Miami, FL, USA","start":{"date-parts":[[2023,5,8]]},"end":{"date-parts":[[2023,5,12]]}},"container-title":["NOMS 2023-2023 IEEE\/IFIP Network Operations and Management Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10154252\/10154208\/10154210.pdf?arnumber=10154210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T23:26:37Z","timestamp":1706052397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10154210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/noms56928.2023.10154210","relation":{},"subject":[],"published":{"date-parts":[[2023,5,8]]}}}