{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:07Z","timestamp":1750220227054,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T00:00:00Z","timestamp":1655856000000},"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":[[2022,6,22]]},"DOI":"10.1145\/3532577.3532601","type":"proceedings-article","created":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T10:07:54Z","timestamp":1655287674000},"page":"105-111","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of Reinforcement-Learning Queue Management Algorithm for Undersea Acoustic Networks Using ns-3"],"prefix":"10.1145","author":[{"given":"Peng","family":"Zhang","sequence":"first","affiliation":[{"name":"Naval Information Warfare Center, Pacific, USA"}]},{"given":"Pedro A.","family":"Forero","sequence":"additional","affiliation":[{"name":"Naval Information Warfare Center, Pacific, USA"}]},{"given":"Daniel","family":"Yap","sequence":"additional","affiliation":[{"name":"Naval Information Warfare Center, Pacific, USA"}]},{"given":"Dusan","family":"Radosevic","sequence":"additional","affiliation":[{"name":"Naval Information Warfare Center, Pacific, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2012.082212.00018"},{"key":"e_1_3_2_1_2_1","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arXiv preprint arXiv:1606.01540(2016).  Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arXiv preprint arXiv:1606.01540(2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Steve\u00a0E. Deering and Robert\u00a0M. Hinden. 2017. Internet Protocol Version 6 (IPv6) Specification. RFC 8200.  Steve\u00a0E. Deering and Robert\u00a0M. Hinden. 2017. Internet Protocol Version 6 (IPv6) Specification. RFC 8200.","DOI":"10.17487\/RFC8200"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.23919\/OCEANS44145.2021.9706025"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3345768.3355908"},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080)","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 Proc. of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080) , Jennifer Dy and Andreas Krause (Eds.). PMLR , 1861\u20131870. 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 Proc. of the 35th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a080), Jennifer Dy and Andreas Krause (Eds.). PMLR, 1861\u20131870."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2006.1683469"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2915371.2915382"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3067665.3067677"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2793964"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3148675.3148679"},{"key":"e_1_3_2_1_12_1","volume-title":"Controlling Queue Delay: A Modern AQM is Just One Piece of the Solution to Bufferbloat.Queue 10, 5 (May","author":"Nichols Kathleen","year":"2012","unstructured":"Kathleen Nichols and Van Jacobson . 2012. Controlling Queue Delay: A Modern AQM is Just One Piece of the Solution to Bufferbloat.Queue 10, 5 (May 2012 ), 20\u201334. Kathleen Nichols and Van Jacobson. 2012. Controlling Queue Delay: A Modern AQM is Just One Piece of the Solution to Bufferbloat.Queue 10, 5 (May 2012), 20\u201334."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Kathleen Nichols Van Jacobson Andrew McGregor and Jana Iyengar. 2018. Controlled Delay Active Queue Management. RFC 8289.  Kathleen Nichols Van Jacobson Andrew McGregor and Jana Iyengar. 2018. Controlled Delay Active Queue Management. RFC 8289.","DOI":"10.17487\/RFC8289"},{"key":"e_1_3_2_1_14_1","first-page":"1","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin Antonin","year":"2021","unstructured":"Antonin Raffin , Ashley Hill , Adam Gleave , Anssi Kanervisto , Maximilian Ernestus , and Noah Dormann . 2021 . Stable-Baselines3: Reliable Reinforcement Learning Implementations . Journal of Machine Learning Research 22 , 268 (2021), 1 \u2013 8 . Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, and Noah Dormann. 2021. Stable-Baselines3: Reliable Reinforcement Learning Implementations. Journal of Machine Learning Research 22, 268 (2021), 1\u20138.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Kadangode\u00a0K. Ramakrishnan Sally Floyd and David\u00a0L. Black. 2001. RFC3168: The Addition of Explicit Congestion Notification (ECN) to IP.  Kadangode\u00a0K. Ramakrishnan Sally Floyd and David\u00a0L. Black. 2001. RFC3168: The Addition of Explicit Congestion Notification (ECN) to IP.","DOI":"10.17487\/rfc3168"},{"volume-title":"The ns-3 Network Simulator","author":"Riley F.","key":"e_1_3_2_1_16_1","unstructured":"George\u00a0 F. Riley and Thomas\u00a0 R. Henderson . 2010. The ns-3 Network Simulator . Springer Berlin Heidelberg, Berlin , Heidelberg , 15\u201334. George\u00a0F. Riley and Thomas\u00a0R. Henderson. 2010. The ns-3 Network Simulator. Springer Berlin Heidelberg, Berlin, Heidelberg, 15\u201334."},{"key":"e_1_3_2_1_17_1","volume-title":"Communication Networks: An Optimization Control, and Stochastic Networks Perspective","author":"Srikant Rayadurgam","year":"2014","unstructured":"Rayadurgam Srikant and Lei Ying . 2014 . Communication Networks: An Optimization Control, and Stochastic Networks Perspective ( 1 st ed.). Cambridge University Press . Rayadurgam Srikant and Lei Ying. 2014. Communication Networks: An Optimization Control, and Stochastic Networks Perspective (1st ed.). Cambridge University Press.","edition":"1"}],"event":{"name":"WNS3 2022: 2022 Workshop on ns-3","acronym":"WNS3 2022","location":"Virtual Event USA"},"container-title":["Proceedings of the 2022 Workshop on ns-3"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532577.3532601","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3532577.3532601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:10Z","timestamp":1750188610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532577.3532601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,22]]},"references-count":17,"alternative-id":["10.1145\/3532577.3532601","10.1145\/3532577"],"URL":"https:\/\/doi.org\/10.1145\/3532577.3532601","relation":{},"subject":[],"published":{"date-parts":[[2022,6,22]]},"assertion":[{"value":"2022-06-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}