{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:17:05Z","timestamp":1774595825670,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/ieeeconf67917.2025.11443757","type":"proceedings-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:47:37Z","timestamp":1774554457000},"page":"1817-1823","source":"Crossref","is-referenced-by-count":0,"title":["A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications"],"prefix":"10.1109","author":[{"given":"Ozan","family":"Ayg\u00fcn","sequence":"first","affiliation":[{"name":"New York University,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincenzo Norman","family":"Vitale","sequence":"additional","affiliation":[{"name":"Università Degli Studi Napoli Federico II,Naples,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonia M.","family":"Tulino","sequence":"additional","affiliation":[{"name":"New York University,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Feng","sequence":"additional","affiliation":[{"name":"Intel Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elza","family":"Erkip","sequence":"additional","affiliation":[{"name":"New York University,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Llorca","sequence":"additional","affiliation":[{"name":"Università Degli Studi di Trento,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/6GNet54646.2022.9830429"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1990.204000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79995-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2783846"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3070699"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2874671"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3179349"},{"key":"ref8","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume":"6","author":"Boyan","year":"1993","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913776"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3529375"},{"key":"ref11","first-page":"1","article-title":"Reinforcement learning for multi-hop scheduling and routing of real-time flows","volume-title":"2020 18th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT)","author":"HasanzadeZonuzy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3012832"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP52444.2021.9651934"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2256682"},{"key":"ref15","first-page":"10170","article-title":"Model-free reinforcement learning in infinite-horizon average-reward markov decision processes","volume-title":"International conference on machine learning","author":"Wei"},{"key":"ref16","article-title":"Constrained reinforcement learning has zero duality gap","volume":"32","author":"Paternain","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"Stampa","year":"2017"},{"key":"ref19","volume-title":"Reinforcement Learning: An Introduction.","author":"Sutton","year":"2018"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref21","article-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","author":"Engstrom","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3124812"}],"event":{"name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2025,10,26]]},"end":{"date-parts":[[2025,10,29]]}},"container-title":["2025 59th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443114\/11443296\/11443757.pdf?arnumber=11443757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:48:35Z","timestamp":1774590515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf67917.2025.11443757","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}