{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:54:37Z","timestamp":1781675677672,"version":"3.54.5"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"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":[[2026,4,13]]},"DOI":"10.1109\/wcnc65185.2026.11555332","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:41:29Z","timestamp":1781638889000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SABR: A Stable Adaptive Bitrate Framework Using Behavior Cloning Pretraining and Reinforcement Learning Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Pengcheng","family":"Luo","sequence":"first","affiliation":[{"name":"Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genke","family":"Yang","sequence":"additional","affiliation":[{"name":"Ningbo Artificial Intelligence Institute, Shanghai Jiao Tong University,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boon-Hee","family":"Soong","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chau","family":"Yuen","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300845"},{"key":"ref2","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref6","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref8","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611771"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672268"},{"issue":"2","key":"ref14","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref15","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross","year":"2011"},{"key":"ref16","volume-title":"Comyco for linear-based QoE (comyco-lin)","author":"Huang","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref18","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472923"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3419394.3423629"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2483977.2483991"},{"key":"ref22","volume-title":"Raw data measuring broadband america 2016","year":"2016"},{"key":"ref23","volume-title":"Raw data releases - measuring broadband america 2018","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350866"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230558"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548331"},{"key":"ref27","first-page":"495","article-title":"Learning in situ: a randomized experiment in video streaming","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Yan","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796948"},{"key":"ref29","volume-title":"dash.js: Mpeg-dash reference client","year":"2012"},{"key":"ref30","volume-title":"Big buck bunny","year":"2008"},{"key":"ref31","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"issue":"268","key":"ref32","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":"ref33","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2996964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123390"}],"event":{"name":"2026 IEEE Wireless Communications and Networking Conference (WCNC)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2026,4,13]]},"end":{"date-parts":[[2026,4,16]]}},"container-title":["2026 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11555037\/11555040\/11555332.pdf?arnumber=11555332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:20:28Z","timestamp":1781673628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11555332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/wcnc65185.2026.11555332","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]}}}