{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T01:10:45Z","timestamp":1776474645781,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730089","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"948-957","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Techie: Tackling Video Prefetching at Edge Networks as POMDP Via an Intrinsically Motivated RL Agent"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6584-4431","authenticated-orcid":false,"given":"Nawras","family":"Alkassab","sequence":"first","affiliation":[{"name":"University of South Carolina, Columbia, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3983-972X","authenticated-orcid":false,"given":"Chin-Tser","family":"Huang","sequence":"additional","affiliation":[{"name":"University of South Carolina, Columbia, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8836-3983","authenticated-orcid":false,"given":"Tania","family":"Lorido Botran","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA and Roblox, Sam Mateo, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3252365"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21041292"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1943552.1943574"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230558"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN61486.2024.10637652"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3193856"},{"key":"e_1_3_2_1_7_1","volume-title":"Openai gym","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. Openai gym, 2016."},{"key":"e_1_3_2_1_8_1","volume-title":"Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355","author":"Burda Yuri","year":"2018","unstructured":"Yuri Burda, Harri Edwards, Deepak Pathak, Amos Storkey, Trevor Darrell, and Alexei A Efros. Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355, 2018."},{"key":"e_1_3_2_1_9_1","volume-title":"Intrinsically motivated reinforcement learning. Advances in neural information processing systems, 17","author":"Chentanez Nuttapong","year":"2004","unstructured":"Nuttapong Chentanez, Andrew Barto, and Satinder Singh. Intrinsically motivated reinforcement learning. Advances in neural information processing systems, 17, 2004."},{"key":"e_1_3_2_1_10_1","unstructured":"Kyunghyun Cho Bart Van Merri\u00ebnboer Caglar Gulcehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 2014."},{"key":"e_1_3_2_1_11_1","volume-title":"Understanding the impact of video quality on user engagement. ACM SIGCOMM computer communication review, 41(4):362--373","author":"Dobrian Florin","year":"2011","unstructured":"Florin Dobrian, Vyas Sekar, Asad Awan, Ion Stoica, Dilip Joseph, Aditya Ganjam, Jibin Zhan, and Hui Zhang. Understanding the impact of video quality on user engagement. ACM SIGCOMM computer communication review, 41(4):362--373, 2011."},{"key":"e_1_3_2_1_12_1","volume-title":"Deep transformer q-networks for partially observable reinforcement learning. arXiv preprint arXiv:2206.01078","author":"Esslinger Kevin","year":"2022","unstructured":"Kevin Esslinger, Robert Platt, and Christopher Amato. Deep transformer q-networks for partially observable reinforcement learning. arXiv preprint arXiv:2206.01078, 2022."},{"key":"e_1_3_2_1_13_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):19","author":"Maxwell Harper F","year":"2016","unstructured":"F Maxwell Harper and Joseph A Konstan. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):19, 2016."},{"key":"e_1_3_2_1_14_1","volume-title":"Deep recurrent q-learning for partially observable mdps. arXiv preprint arXiv:1507.06527","author":"Hausknecht Matthew","year":"2015","unstructured":"Matthew Hausknecht and Peter Stone. Deep recurrent q-learning for partially observable mdps. arXiv preprint arXiv:1507.06527, 2015."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2398776.2398800"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2413176.2413189"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1878022.1878030"},{"key":"e_1_3_2_1_19_1","volume-title":"The budgeted maximum coverage problem. Information processing letters, 70(1):39--45","author":"Khuller Samir","year":"1999","unstructured":"Samir Khuller, Anna Moss, and Joseph Seffi Naor. The budgeted maximum coverage problem. Information processing letters, 70(1):39--45, 1999."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2903722"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2713168.2713181"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_23_1","volume-title":"Human-level control through deep reinforcement learning. nature, 518(7540):529--533","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. Human-level control through deep reinforcement learning. nature, 518(7540):529--533, 2015."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/INM.2011.5990550"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2018602.2018611"},{"key":"e_1_3_2_1_26_1","volume-title":"Recurrent model-free rl can be a strong baseline for many pomdps. arXiv preprint arXiv:2110.05038","author":"Ni Tianwei","year":"2021","unstructured":"Tianwei Ni, Benjamin Eysenbach, and Ruslan Salakhutdinov. Recurrent model-free rl can be a strong baseline for many pomdps. arXiv preprint arXiv:2110.05038, 2021."},{"key":"e_1_3_2_1_27_1","volume-title":"Github Repository","author":"Pleines Marco","year":"2023","unstructured":"Marco Pleines, Matthias Pallasch, Frank Zimmer, and Mike Preuss. Transformerxl as episodic memory in proximal policy optimization. Github Repository, 2023."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540090600768658"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329051"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3029893"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2011.71"},{"key":"e_1_3_2_1_32_1","volume-title":"Bola: Near-optimal bitrate adaptation for online videos","author":"Spiteri Kevin","year":"2020","unstructured":"Kevin Spiteri, Rahul Urgaonkar, and Ramesh K Sitaraman. Bola: Near-optimal bitrate adaptation for online videos. IEEE\/ACM transactions on networking, 28(4):1698--1711, 2020."},{"key":"e_1_3_2_1_33_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","year":"2018","unstructured":"Richard S Sutton and Andrew G Barto. Reinforcement learning: An introduction. MIT press, 2018."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(03)00062-2"},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2237022"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/76.911156"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947067"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/6046.944477"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:33:28Z","timestamp":1755887608000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":40,"alternative-id":["10.1145\/3726302.3730089","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730089","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}