{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:00:51Z","timestamp":1775066451484,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"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":[[2022,4,25]]},"DOI":"10.1109\/noms54207.2022.9789945","type":"proceedings-article","created":{"date-parts":[[2022,6,9]],"date-time":"2022-06-09T21:21:22Z","timestamp":1654809682000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies"],"prefix":"10.1109","author":[{"given":"Carlos","family":"Guemes-Palau","sequence":"first","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Neural Networking Center,Spain"}]},{"given":"Paul","family":"Almasan","sequence":"additional","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Neural Networking Center,Spain"}]},{"given":"Shihan","family":"Xiao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co.,Ltd.,Network Technology Lab."}]},{"given":"Xiangle","family":"Cheng","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co.,Ltd.,Network Technology Lab."}]},{"given":"Xiang","family":"Shi","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1364\/JON.3.000363"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5121\/ijcnc.2012.4202"},{"key":"ref12","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017"},{"key":"ref13","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/35.900635"},{"key":"ref15","first-page":"1","article-title":"Deep-RMSA: A Deep-Reinforcement-Learning Routing, Modulation and Spectrum Assignment Agent for Elastic Optical Networks","author":"chen","year":"2018","journal-title":"The Optical Fiber Communication Conference and Exposition (OFC)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.11.000547"},{"key":"ref17","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics JMLR Workshop and Conference Proceedings"},{"key":"ref18","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref19","article-title":"NetworkX","author":"developers","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00098"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472902"},{"key":"ref27","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Int“l Conf on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2014.6964248"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP52444.2021.9651930"},{"key":"ref29","article-title":"Evolutionary reinforcement learning","author":"khadka","year":"2018","journal-title":"CoRR"},{"key":"ref5","article-title":"Enero: Efficient real-time routing optimization","author":"almasan","year":"2021"},{"key":"ref8","article-title":"Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case","author":"almasan","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref2","article-title":"Digital twin network: Opportunities and challenges","author":"almasan","year":"2022"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref1","article-title":"Digital Twin Network: Concepts and Reference Architecture","author":"zhou","year":"2021","journal-title":"Internet Engineering Task Force Internet-Draft draft-zhou-nmrg-digitaltwin-network-concepts-06"},{"key":"ref20","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Int“l Conf on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3083216"},{"key":"ref24","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a gpu","author":"babaeizadeh","year":"2016"},{"key":"ref23","article-title":"Efficient parallel methods for deep reinforcement learning","author":"clemente","year":"2017"},{"key":"ref26","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018"},{"key":"ref25","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018"}],"event":{"name":"NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium","location":"Budapest, Hungary","start":{"date-parts":[[2022,4,25]]},"end":{"date-parts":[[2022,4,29]]}},"container-title":["NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9789703\/9789704\/09789945.pdf?arnumber=9789945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T20:10:11Z","timestamp":1656965411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9789945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/noms54207.2022.9789945","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]}}}