{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:22:00Z","timestamp":1761582120831,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T00:00:00Z","timestamp":1623024000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T00:00:00Z","timestamp":1623024000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004895","name":"European Social Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004895","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,7]]},"DOI":"10.1109\/hpsr52026.2021.9481864","type":"proceedings-article","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T20:47:56Z","timestamp":1629838076000},"page":"1-6","source":"Crossref","is-referenced-by-count":10,"title":["Towards Real-Time Routing Optimization with Deep Reinforcement Learning: Open Challenges"],"prefix":"10.1109","author":[{"given":"Paul","family":"Almasan","sequence":"first","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Neural Networking Center,Spain"}]},{"given":"Jose","family":"Suarez-Varela","sequence":"additional","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Neural Networking Center,Spain"}]},{"given":"Bo","family":"Wu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co.,Ltd.,Network Technology Lab."}]},{"given":"Shihan","family":"Xiao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co.,Ltd.,Network Technology Lab."}]},{"given":"Pere","family":"Barlet-Ros","sequence":"additional","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Neural Networking Center,Spain"}]},{"given":"Albert","family":"Cabellos-Aparicio","sequence":"additional","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Neural Networking Center,Spain"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2016.027"},{"article-title":"Accelerated methods for deep reinforcement learning","year":"2018","author":"stooke","key":"ref32"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1126\/science.220.4598.671","article-title":"Optimization by simulated annealing","volume":"220","author":"kirkpatrick","year":"1983","journal-title":"Science"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1096536.1096551"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3342280.3342327"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2011.2134866"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787495"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8056971"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761276"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3022064"},{"article-title":"Rfc2328: Ospf version 2","year":"1998","author":"moy","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2015.7417124"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICTON.2011.5970940"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1364\/JON.3.000363"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2007.386616"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","article-title":"Mastering atari, go, chess and shogi by planning with a learned model","volume":"588","author":"schrittwieser","year":"2020","journal-title":"Nature"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5121\/ijcnc.2012.4202"},{"year":"0","key":"ref5","article-title":"IBM CPLEX optimizer"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"article-title":"Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case","year":"2019","author":"almasan","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600232CM"},{"article-title":"Relational inductive biases, deep learning, and graph networks","year":"2018","author":"battaglia","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-010-9400-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7158286"},{"key":"ref22","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"gilmer","year":"2017","journal-title":"Proceedings of the International Conference on Machine Learning (ICML) - Volume 70"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref21"},{"key":"ref24","first-page":"265","article-title":"Tensorflow: A system for largescale machine learning","author":"abadi","year":"2016","journal-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI'02)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.11.000547"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref26"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref25"}],"event":{"name":"2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR)","start":{"date-parts":[[2021,6,7]]},"location":"Paris, France","end":{"date-parts":[[2021,6,10]]}},"container-title":["2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9481789\/9481790\/09481864.pdf?arnumber=9481864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:58:30Z","timestamp":1659484710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9481864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/hpsr52026.2021.9481864","relation":{},"subject":[],"published":{"date-parts":[[2021,6,7]]}}}