{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:19:24Z","timestamp":1766067564617,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T00:00:00Z","timestamp":1652659200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T00:00:00Z","timestamp":1652659200000},"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":[[2022,5,16]]},"DOI":"10.1109\/icc45855.2022.9838901","type":"proceedings-article","created":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T19:37:11Z","timestamp":1660246631000},"page":"365-370","source":"Crossref","is-referenced-by-count":4,"title":["ZiXia: A Reinforcement Learning Approach via Adjusted Ranking Reward for Internet Congestion Control"],"prefix":"10.1109","author":[{"given":"Lianchen","family":"Jia","sequence":"first","affiliation":[{"name":"Tsinghua University,Dept. of CS&Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianchi","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of CS&Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of CS&Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155250"},{"key":"ref11","article-title":"Zwei: A self-play reinforcement learning framework for video transmission services","author":"huang","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"article-title":"Reinforcement learning with unsupervised auxiliary tasks","year":"2016","author":"jaderberg","key":"ref12"},{"key":"ref13","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous methods for deep rein-forcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref18"},{"key":"ref19","first-page":"417","article-title":"Mahimahi: Accurate record-and-replay for {HTTP}","author":"netravali","year":"2015","journal-title":"2015 USENIX Annual Technical Conference (ATC 15)"},{"key":"ref4","first-page":"731","article-title":"Pantheon: the training ground for internet congestion-control research","author":"yan","year":"2018","journal-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref6","first-page":"343","article-title":"{PCC} in vivace: Online-learning congestion control","author":"dong","year":"2018","journal-title":"15th USENIX Symposium on Networked Systems Design and Implementation ( NSDI 18)"},{"key":"ref5","first-page":"395","article-title":"PCC : Re-architecting congestion control for consistent high performance","author":"dong","year":"2015","journal-title":"12th USENIX Symposium on Networked Systems Design and Implementation ( NSDI 15)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000603"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"ref9","first-page":"3050","article-title":"A deep reinforcement learning perspective on internet congestion control","author":"jay","year":"2019","journal-title":"International Conference on Machine Learning"},{"article-title":"Adapting auxiliary losses using gradient similarity","year":"2018","author":"du","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"ref21","article-title":"Adaptive auxiliary task weighting for reinforcement learning","volume":"32","author":"lin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.14711\/thesis-991013080355703412","article-title":"Multi-objective congestion control","author":"ma","year":"2021"},{"year":"2016","key":"ref23","article-title":"Raw data measuring broadband america 2016"}],"event":{"name":"ICC 2022 - IEEE International Conference on Communications","start":{"date-parts":[[2022,5,16]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2022,5,20]]}},"container-title":["ICC 2022 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9837954\/9838246\/09838901.pdf?arnumber=9838901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T20:04:35Z","timestamp":1663013075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9838901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,16]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icc45855.2022.9838901","relation":{},"subject":[],"published":{"date-parts":[[2022,5,16]]}}}