{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T04:25:46Z","timestamp":1760502346796,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001843","name":"SERB","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,4]]},"DOI":"10.1109\/comsnets53615.2022.9668424","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:03Z","timestamp":1642106343000},"page":"353-361","source":"Crossref","is-referenced-by-count":9,"title":["SAC-ABR: Soft Actor-Critic based deep reinforcement learning for Adaptive BitRate streaming"],"prefix":"10.1109","author":[{"given":"Mandan","family":"Naresh","sequence":"first","affiliation":[{"name":"BITS Pilani,Dept. of CSIS,Hyderabad,India"}]},{"given":"Nandiraju","family":"Gireesh","sequence":"additional","affiliation":[{"name":"BITS Pilani,Dept. of CSIS,Hyderabad,India"}]},{"given":"Paresh","family":"Saxena","sequence":"additional","affiliation":[{"name":"BITS Pilani,Dept. of CSIS,Hyderabad,India"}]},{"given":"Manik","family":"Gupta","sequence":"additional","affiliation":[{"name":"BITS Pilani,Dept. of CSIS,Hyderabad,India"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"},{"key":"ref11","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015","journal-title":"software available from tensorflow org"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356083"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230558"},{"key":"ref14","article-title":"Qtcp: Adaptive congestion control with reinforcement learning, department of electrical and computer engineering, northeastern university, boston","author":"li","year":"0","journal-title":"GLOBE-COM 2020 – 2020 IEEE Global Commun Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413189"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3336497"},{"journal-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"mnih","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322332"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA51439.2020.9264312"},{"journal-title":"ISO\/IEC 23009–1 2014 Dynamic adaptive streaming over HTTP(DASH) - Part 1 Media presentation description and segment formats","year":"2014","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2862938"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref6"},{"journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524428"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626296"},{"journal-title":"Sandvine Global Internet Phenomena Report (2021)","year":"2021","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934898"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref20"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2019","author":"lillicrap","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356052"},{"key":"ref24","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"journal-title":"Addressing Function Approximation Error in Actor-Critic Methods","year":"2018","author":"fujimoto","key":"ref23"},{"key":"ref26","first-page":"417","article-title":"Mahimahi: Accurate record-and-replay for http","author":"netravali","year":"2015","journal-title":"ser USENIX ATC '15 USA USENIX Association"},{"journal-title":"Optimism in reinforcement learning and kullback -leibler divergence","year":"2011","author":"filippi","key":"ref25"}],"event":{"name":"2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS)","start":{"date-parts":[[2022,1,4]]},"location":"Bangalore, India","end":{"date-parts":[[2022,1,8]]}},"container-title":["2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9668311\/9667790\/09668424.pdf?arnumber=9668424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:22:43Z","timestamp":1654546963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9668424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/comsnets53615.2022.9668424","relation":{},"subject":[],"published":{"date-parts":[[2022,1,4]]}}}