{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T04:35:24Z","timestamp":1782016524693,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100013105","name":"Shanghai Rising-Star Program","doi-asserted-by":"publisher","award":["20QA1404600"],"award-info":[{"award-number":["20QA1404600"]}],"id":[{"id":"10.13039\/501100013105","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61931023, 61831018, 61871267, 62120106007, 61972256, T2122024, 62125109"],"award-info":[{"award-number":["61931023, 61831018, 61871267, 62120106007, 61972256, T2122024, 62125109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548331","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:43:12Z","timestamp":1665416592000},"page":"3006-3016","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":47,"title":["Improving Generalization for Neural Adaptive Video Streaming via Meta Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Nuowen","family":"Kan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuankun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junni","family":"Zou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230558"},{"key":"e_1_3_2_2_2_1","unstructured":"Federal Communications Commission. 2016. Raw Data - Measuring Broadband America. (2016). https:\/\/www.fcc.gov\/reports-research\/reports\/measuring-broadband-america\/raw-data-measuring-broadband-america-2016  Federal Communications Commission. 2016. Raw Data - Measuring Broadband America. (2016). https:\/\/www.fcc.gov\/reports-research\/reports\/measuring-broadband-america\/raw-data-measuring-broadband-america-2016"},{"key":"e_1_3_2_2_3_1","volume-title":"International conference on machine learning. PMLR, 1126--1135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn , Pieter Abbeel , and Sergey Levine . 2017 . Model-agnostic meta-learning for fast adaptation of deep networks . In International conference on machine learning. PMLR, 1126--1135 . Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 1126--1135."},{"key":"e_1_3_2_2_4_1","unstructured":"Dash Industry Forum. 2022. Catalyzing the Adoption of MPEG-DASH. https:\/\/dashif.org\/  Dash Industry Forum. 2022. Catalyzing the Adoption of MPEG-DASH. https:\/\/dashif.org\/"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2755007"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning. 1861--1870","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja , Aurick Zhou , Pieter Abbeel , and Sergey Levine . 2018 . Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor . In Proceedings of the 35th International Conference on Machine Learning. 1861--1870 . Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. In Proceedings of the 35th International Conference on Machine Learning. 1861--1870."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000363"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351014"},{"key":"e_1_3_2_2_9_1","unstructured":"Apple Inc. 2022. HTTP Live Streaming. https:\/\/developer.apple.com\/streaming\/  Apple Inc. 2022. HTTP Live Streaming. https:\/\/developer.apple.com\/streaming\/"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458306.3458872"},{"key":"e_1_3_2_2_11_1","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-Encoding Variational Bayes. arxiv: 1312.6114 [cs.LG]  Diederik P Kingma and Max Welling. 2013. Auto-Encoding Variational Bayes. arxiv: 1312.6114 [cs.LG]"},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of International Conference on Learning Representations. 1--12","author":"Lyle Clare","year":"2022","unstructured":"Clare Lyle , Mark Rowland , and Will Dabney . 2022 . Understanding and Preventing Capacity Loss in Reinforcement Learning . In Proceedings of International Conference on Learning Representations. 1--12 . Clare Lyle, Mark Rowland, and Will Dabney. 2022. Understanding and Preventing Capacity Loss in Reinforcement Learning. In Proceedings of International Conference on Learning Representations. 1--12."},{"key":"e_1_3_2_2_13_1","volume-title":"Real-world Video Adaptation with Reinforcement Learning. arxiv","author":"Mao Hongzi","year":"2008","unstructured":"Hongzi Mao , Shannon Chen , Drew Dimmery , Shaun Singh , Drew Blaisdell , Yuandong Tian , Mohammad Alizadeh , and Eytan Bakshy . 2020. Real-world Video Adaptation with Reinforcement Learning. arxiv : 2008 .12858 [cs.NI] Hongzi Mao, Shannon Chen, Drew Dimmery, Shaun Singh, Drew Blaisdell, Yuandong Tian, Mohammad Alizadeh, and Eytan Bakshy. 2020. Real-world Video Adaptation with Reinforcement Learning. arxiv: 2008.12858 [cs.NI]"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_2_15_1","volume-title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning. In 2018 IEEE International Conference on Robotics and Automation (ICRA). 7559--7566","author":"Nagabandi Anusha","year":"2018","unstructured":"Anusha Nagabandi , Gregory Kahn , Ronald S. Fearing , and Sergey Levine . 2018 . Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning. In 2018 IEEE International Conference on Robotics and Automation (ICRA). 7559--7566 . Anusha Nagabandi, Gregory Kahn, Ronald S. Fearing, and Sergey Levine. 2018. Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning. In 2018 IEEE International Conference on Robotics and Automation (ICRA). 7559--7566."},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 36th International conference on machine learning. 5331--5340","author":"Rakelly Kate","year":"2019","unstructured":"Kate Rakelly , Aurick Zhou , Chelsea Finn , Sergey Levine , and Deirdre Quillen . 2019 . Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables . In Proceedings of the 36th International conference on machine learning. 5331--5340 . Kate Rakelly, Aurick Zhou, Chelsea Finn, Sergey Levine, and Deirdre Quillen. 2019. Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables. In Proceedings of the 36th International conference on machine learning. 5331--5340."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2483977.2483991"},{"key":"e_1_3_2_2_18_1","unstructured":"John Schulman Philipp Moritz Sergey Levine Michael Jordan and Pieter Abbeel. 2018. High-Dimensional Continuous Control Using Generalized Advantage Estimation. arxiv: 1506.02438 [cs.LG]  John Schulman Philipp Moritz Sergey Levine Michael Jordan and Pieter Abbeel. 2018. High-Dimensional Continuous Control Using Generalized Advantage Estimation. arxiv: 1506.02438 [cs.LG]"},{"key":"e_1_3_2_2_19_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arxiv: 1707.06347 [cs.LG]  John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arxiv: 1707.06347 [cs.LG]"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2011.71"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524428"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934898"},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Yan Francis Y.","year":"2020","unstructured":"Francis Y. Yan , Hudson Ayers , Chenzhi Zhu , Sadjad Fouladi , James Hong , Keyi Zhang , Philip Levis , and Keith Winstein . 2020 . Learning in situ: A Randomized Experiment in Video Streaming . In Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20) . 495--511. Francis Y. Yan, Hudson Ayers, Chenzhi Zhu, Sadjad Fouladi, James Hong, Keyi Zhang, Philip Levis, and Keith Winstein. 2020. Learning in situ: A Randomized Experiment in Video Streaming. In Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 495--511."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548331","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:43Z","timestamp":1750186843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":24,"alternative-id":["10.1145\/3503161.3548331","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548331","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}