{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:15:53Z","timestamp":1755839753151,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"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":[[2024,5,20]]},"DOI":"10.1109\/infocom52122.2024.10621126","type":"proceedings-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T17:25:41Z","timestamp":1723483541000},"page":"2169-2178","source":"Crossref","is-referenced-by-count":2,"title":["Dancing with Shackles, Meet the Challenge of Industrial Adaptive Streaming via Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lianchen","family":"Jia","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Chao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing Kuaishou Technology Co., Ltd"}]},{"given":"Tianchi","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Chaoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Lifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230558"},{"article-title":"Causalsim: Toward a causal data-driven simulator for network protocols","year":"2022","author":"Alomar","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626296"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228995"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413189"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref7"},{"volume-title":"Announcement of the results for the year ended december 31","year":"2022","key":"ref8"},{"key":"ref9","first-page":"3703","article-title":"Batch policy learning under constraints","volume-title":"International Conference on Machine Learning","author":"Le"},{"article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"Levine","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.140405"},{"key":"ref12","first-page":"6266","article-title":"Curriculum offline imitating learning","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","year":"2019","author":"Peng","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3210445.3210453"},{"year":"2022","key":"ref16","article-title":"The 2022 global internet phenomena report"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2996964"},{"article-title":"Empirical study of off-policy policy evaluation for reinforcement learning","year":"2019","author":"Voloshin","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087270"},{"key":"ref20","first-page":"495","article-title":"Learning in situ: a randomized experiment in video streaming","volume":"20","author":"Yan","year":"2020","journal-title":"NSDI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419195"},{"key":"ref23","first-page":"22302","article-title":"Quality-aware pre-trained models for blind image quality assessment","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhao"}],"event":{"name":"IEEE INFOCOM 2024 - IEEE Conference on Computer Communications","start":{"date-parts":[[2024,5,20]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2024,5,23]]}},"container-title":["IEEE INFOCOM 2024 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10621050\/10621073\/10621126.pdf?arnumber=10621126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:43:49Z","timestamp":1723527829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10621126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/infocom52122.2024.10621126","relation":{},"subject":[],"published":{"date-parts":[[2024,5,20]]}}}