{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:29:58Z","timestamp":1730280598644,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T00:00:00Z","timestamp":1637107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T00:00:00Z","timestamp":1637107200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T00:00:00Z","timestamp":1637107200000},"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":[[2021,11,17]]},"DOI":"10.1109\/latincom53176.2021.9647836","type":"proceedings-article","created":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T18:04:48Z","timestamp":1640282688000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Rainbow deep reinforcement learning for TCP congestion control"],"prefix":"10.1109","author":[{"given":"Jean P.","family":"Martins","sequence":"first","affiliation":[]},{"given":"Ricardo S.","family":"Souza","sequence":"additional","affiliation":[]},{"given":"Igor","family":"Almeida","sequence":"additional","affiliation":[]},{"given":"Silvia","family":"Lins","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2914"},{"key":"ref11","article-title":"The Addition of Explicit Congestion Notification (ECN) to IP","author":"floyd","year":"2001","journal-title":"RFC 3168"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.17487\/RFC8257"},{"key":"ref13","first-page":"343356","article-title":"Pcc vivace: Online-learning congestion control","author":"dong","year":"2018","journal-title":"Proceedings of the 15th USENIX Conference on Networked Systems Design and Implementation"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2835758"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2892046"},{"key":"ref16","article-title":"The NewReno Modification to TCP’s Fast Recovery Algorithm","author":"gurtov","year":"2012","journal-title":"RFC 6582"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref18","article-title":"ns3-gym: Extending openai gym for networking research","volume":"abs 1810 3943","author":"gawlowicz","year":"2018","journal-title":"CoRR"},{"key":"ref19","first-page":"561577","article-title":"Ray: A distributed framework for emerging ai applications","author":"moritz","year":"2018","journal-title":"Proceedings of the 12th USENIX conference on operating systems design and implementation"},{"key":"ref4","article-title":"Rainbow: Combining improvements in deep reinforcement learning","volume":"abs 1710 2298","author":"hessel","year":"2017","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"article-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref6"},{"key":"ref5","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"2016","journal-title":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence"},{"key":"ref8","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70"},{"key":"ref7","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref9","article-title":"Noisy networks for exploration","volume":"abs 1706 10295","author":"fortunato","year":"2017","journal-title":"CoRR"},{"article-title":"Rllib: Abstractions for distributed reinforcement learning","year":"2017","author":"liang","key":"ref20"}],"event":{"name":"2021 IEEE Latin-American Conference on Communications (LATINCOM)","start":{"date-parts":[[2021,11,17]]},"location":"Santo Domingo, Dominican Republic","end":{"date-parts":[[2021,11,19]]}},"container-title":["2021 IEEE Latin-American Conference on Communications (LATINCOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9647714\/9647733\/09647836.pdf?arnumber=9647836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:59:46Z","timestamp":1652187586000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9647836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,17]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/latincom53176.2021.9647836","relation":{},"subject":[],"published":{"date-parts":[[2021,11,17]]}}}