{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:38:21Z","timestamp":1781887101818,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,15]]},"DOI":"10.1145\/3625468.3653068","type":"proceedings-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T06:10:01Z","timestamp":1713334201000},"page":"339-345","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["ACM MMSys 2024 Bandwidth Estimation in Real Time Communications Challenge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6730-7267","authenticated-orcid":false,"given":"Sami","family":"Khairy","sequence":"first","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2129-2414","authenticated-orcid":false,"given":"Gabriel","family":"Mittag","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3887-1439","authenticated-orcid":false,"given":"Vishak","family":"Gopal","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2123-4258","authenticated-orcid":false,"given":"Francis Y.","family":"Yan","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6947-9740","authenticated-orcid":false,"given":"Zhixiong","family":"Niu","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4479-9557","authenticated-orcid":false,"given":"Ezra","family":"Ameri","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3768-0296","authenticated-orcid":false,"given":"Scott","family":"Inglis","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9827-6496","authenticated-orcid":false,"given":"Mehrsa","family":"Golestaneh","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2004-3003","authenticated-orcid":false,"given":"Ross","family":"Cutler","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"BoB: Bandwidth prediction for real-time communications using heuristic and reinforcement learning","author":"Bentaleb Abdelhak","year":"2022","unstructured":"Abdelhak Bentaleb, Mehmet N Akcay, May Lim, Ali C Begen, and Roger Zimmermann. 2022. BoB: Bandwidth prediction for real-time communications using heuristic and reinforcement learning. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 15th ACM Multimedia Systems Conference.","author":"Cetinkaya Ekrem","unstructured":"Ekrem Cetinkaya, Ahmet Pehlivanoglu, Ihsan U. Ayten, Basar Yumakogullari, Mehmet E. Ozgun, Yigit K. Erinc, Enes Deniz, and Ali C. Begen. 2024. Offline Reinforcement Learning for Bandwidth Estimation in RTC Using a Fast Actor and not-So-Furious Critic. In Proceedings of the 15th ACM Multimedia Systems Conference."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542637.3542648"},{"key":"e_1_3_2_1_4_1","first-page":"8591","article-title":"A closer look at offline rl agents","volume":"35","author":"Fu Yuwei","year":"2022","unstructured":"Yuwei Fu, Di Wu, and Benoit Boulet. 2022. A closer look at offline rl agents. Advances in Neural Information Processing Systems 35 (2022), 8591--8604.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","volume-title":"A minimalist approach to offline reinforcement learning. Advances in neural information processing systems 34","author":"Fujimoto Scott","year":"2021","unstructured":"Scott Fujimoto and Shixiang Shane Gu. 2021. A minimalist approach to offline reinforcement learning. Advances in neural information processing systems 34 (2021), 20132--20145."},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-policy deep reinforcement learning without exploration. In International conference on machine learning. PMLR, 2052--2062."},{"key":"e_1_3_2_1_7_1","volume-title":"Real-time Bandwidth Estimation from Offline Expert Demonstrations. arXiv preprint arXiv:2309.13481","author":"Gottipati Aashish","year":"2023","unstructured":"Aashish Gottipati, Sami Khairy, Gabriel Mittag, Vishak Gopal, and Ross Cutler. 2023. Real-time Bandwidth Estimation from Offline Expert Demonstrations. arXiv preprint arXiv:2309.13481 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 5774--5783","author":"Kostrikov Ilya","year":"2021","unstructured":"Ilya Kostrikov, Rob Fergus, Jonathan Tompson, and Ofir Nachum. 2021. Offline reinforcement learning with fisher divergence critic regularization. In International Conference on Machine Learning. PMLR, 5774--5783."},{"key":"e_1_3_2_1_9_1","volume-title":"Stabilizing off-policy q-learning via bootstrapping error reduction. Advances in Neural Information Processing Systems 32","author":"Kumar Aviral","year":"2019","unstructured":"Aviral Kumar, Justin Fu, Matthew Soh, George Tucker, and Sergey Levine. 2019. Stabilizing off-policy q-learning via bootstrapping error reduction. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_10_1","volume-title":"When should we prefer offline reinforcement learning over behavioral cloning? arXiv preprint arXiv:2204.05618","author":"Kumar Aviral","year":"2022","unstructured":"Aviral Kumar, Joey Hong, Anikait Singh, and Sergey Levine. 2022. When should we prefer offline reinforcement learning over behavioral cloning? arXiv preprint arXiv:2204.05618 (2022)."},{"key":"e_1_3_2_1_11_1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative q-learning for offline reinforcement learning. Advances in Neural Information Processing Systems 33 (2020), 1179--1191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"Reinforcement learning: State-of-the-art","author":"Lange Sascha","unstructured":"Sascha Lange, Thomas Gabel, and Martin Riedmiller. 2012. Batch reinforcement learning. In Reinforcement learning: State-of-the-art. Springer, 45--73."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB55706.2022.9828569"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB55706.2022.9828569"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB55706.2022.9828569"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3652174"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPSR57248.2023.10147986"},{"key":"e_1_3_2_1_18_1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Mittag Gabriel","unstructured":"Gabriel Mittag, Babak Naderi, Vishak Gopal, and Ross Cutler. 2023. LSTM-Based Video Quality Prediction Accounting for Temporal Distortions in Videoconferencing Calls. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_1_19_1","volume-title":"Yi Ma, Chelsea Finn, Aviral Kumar, and Sergey Levine.","author":"Nakamoto Mitsuhiko","year":"2024","unstructured":"Mitsuhiko Nakamoto, Simon Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, and Sergey Levine. 2024. Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.17487\/RFC3550"},{"key":"e_1_3_2_1_21_1","volume-title":"ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints. Advances in Neural Information Processing Systems 36","author":"Singh Anikait","year":"2024","unstructured":"Anikait Singh, Aviral Kumar, Quan Vuong, Yevgen Chebotar, and Sergey Levine. 2024. ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3652183"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458305.3479970"},{"key":"e_1_3_2_1_25_1","unstructured":"Shibo Wang Hairong Su Qiang Su Shusen Yang and Hong Xu. 2024. Drawing Insights from Congestion Control Research: An Effortless Bitrate Adaptation Approach for Real-Time Communication."},{"key":"e_1_3_2_1_26_1","first-page":"7768","article-title":"Critic regularized regression","volume":"33","author":"Wang Ziyu","year":"2020","unstructured":"Ziyu Wang, Alexander Novikov, Konrad Zolna, Josh S Merel, Jost Tobias Springenberg, Scott E Reed, Bobak Shahriari, Noah Siegel, Caglar Gulcehre, Nicolas Heess, et al. 2020. Critic regularized regression. Advances in Neural Information Processing Systems 33 (2020), 7768--7778.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","volume-title":"Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361","author":"Wu Yifan","year":"2019","unstructured":"Yifan Wu, George Tucker, and Ofir Nachum. 2019. Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361 (2019)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604838"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419186"}],"event":{"name":"MMSys '24: ACM Multimedia Systems Conference 2024","location":"Bari Italy","acronym":"MMSys '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the ACM Multimedia Systems Conference 2024 on ZZZ"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625468.3653068","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3625468.3653068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:27:26Z","timestamp":1755883646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625468.3653068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":29,"alternative-id":["10.1145\/3625468.3653068","10.1145\/3625468"],"URL":"https:\/\/doi.org\/10.1145\/3625468.3653068","relation":{},"subject":[],"published":{"date-parts":[[2024,4,15]]},"assertion":[{"value":"2024-04-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}