{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T09:06:39Z","timestamp":1782378399323,"version":"3.54.5"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/icc40277.2020.9149287","type":"proceedings-article","created":{"date-parts":[[2020,7,27]],"date-time":"2020-07-27T22:26:45Z","timestamp":1595888805000},"page":"1-7","source":"Crossref","is-referenced-by-count":14,"title":["Hierarchical Deep Double Q-Routing"],"prefix":"10.1109","author":[{"given":"Ramy E.","family":"Ali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bilgehan","family":"Erman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ejder","family":"Bastug","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruce","family":"Cilli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11796","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref12","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","author":"boyan","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"231","article-title":"Dual reinforcement q-routing: An online adaptive routing algorithm","author":"kumar","year":"1997","journal-title":"Proceedings of the Artificial Neural Networks in Engineering Conference"},{"key":"ref14","first-page":"832","article-title":"Ants and reinforcement learning: A case study in routing in dynamic networks","author":"subramanian","year":"1997","journal-title":"IJCAI (2)"},{"key":"ref15","first-page":"945","article-title":"Predictive q-routing: A memory-based reinforcement learning approach to adaptive traffic control","author":"choi","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SCC.2016.12"},{"key":"ref17","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"stampa","year":"2017","journal-title":"arXiv preprint arXiv 1709 07492"},{"key":"ref18","article-title":"Learning to route with deep rl","author":"valadarsky","year":"2017","journal-title":"Proc NIPS Symp Deep Reinforcement Learn"},{"key":"ref19","first-page":"14","article-title":"Deep reinforcement learning based qos-aware routing in knowledge-defined networking","author":"pham","year":"2018","journal-title":"International Conference on Heterogeneous Networking for Quality Reliability Security and Robustness"},{"key":"ref4","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref27","article-title":"RMSprop: Divide the gradient by a running average of its recent magnitude","author":"hinton","year":"0","journal-title":"Lecture on Neural Networks for Machine Learning"},{"key":"ref3","article-title":"A path computation element (PCE)-based architecture","author":"ash","year":"2006","journal-title":"IETF RFC4655"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref5","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref7","first-page":"169","article-title":"The effect of correlated input data on the dynamics of learning","author":"halkj\u00e6r","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.17487\/RFC8402"},{"key":"ref9","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05952"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3975(97)00198-9"},{"key":"ref20","author":"mao","year":"2018","journal-title":"Reward design in cooperative multi-agent reinforcement learning for packet routing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761276"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref24","article-title":"Learning multi-agent communication under limited-bandwidth restriction for internet packet routing","author":"mao","year":"2019","journal-title":"arXiv preprint arXiv 1903 00066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3342280.3342317"},{"key":"ref26","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144110"}],"event":{"name":"ICC 2020 - 2020 IEEE International Conference on Communications (ICC)","location":"Dublin, Ireland","start":{"date-parts":[[2020,6,7]]},"end":{"date-parts":[[2020,6,11]]}},"container-title":["ICC 2020 - 2020 IEEE International Conference on Communications (ICC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9141367\/9148588\/09149287.pdf?arnumber=9149287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T19:25:06Z","timestamp":1667589906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9149287\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icc40277.2020.9149287","relation":{},"subject":[],"published":{"date-parts":[[2020,6]]}}}