{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T14:43:25Z","timestamp":1774277005932,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"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":[[2022,1,8]]},"DOI":"10.1109\/ccnc49033.2022.9700657","type":"proceedings-article","created":{"date-parts":[[2022,2,10]],"date-time":"2022-02-10T20:29:11Z","timestamp":1644524951000},"page":"207-215","source":"Crossref","is-referenced-by-count":16,"title":["Constrained Deep Reinforcement Learning for Smart Load Balancing"],"prefix":"10.1109","author":[{"given":"Omar","family":"Houidi","sequence":"first","affiliation":[{"name":"Institut Mines-Telecom, Institut Polytechnique de Paris,Telecom SudParis, Samovar-Lab,France"}]},{"given":"Djamal","family":"Zeghlache","sequence":"additional","affiliation":[{"name":"Institut Mines-Telecom, Institut Polytechnique de Paris,Telecom SudParis, Samovar-Lab,France"}]},{"given":"Victor","family":"Perrier","sequence":"additional","affiliation":[{"name":"Huawei Technologies Ltd,Paris Research Center,France"}]},{"given":"Pham Tran","family":"Anh Quang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Ltd,Paris Research Center,France"}]},{"given":"Nicolas","family":"Huin","sequence":"additional","affiliation":[{"name":"Huawei Technologies Ltd,Paris Research Center,France"}]},{"given":"Jeremie","family":"Leguay","sequence":"additional","affiliation":[{"name":"Huawei Technologies Ltd,Paris Research Center,France"}]},{"given":"Paolo","family":"Medagliani","sequence":"additional","affiliation":[{"name":"Huawei Technologies Ltd,Paris Research Center,France"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc ICML"},{"key":"ref11","first-page":"2137","article-title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"2974","article-title":"Counterfactual Multi-Agent Policy Gradients","author":"foerster","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.01.252"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322277"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-021-05621-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2834050.2834107"},{"key":"ref17","article-title":"Let it flow: Resilient asymmetric load balancing with flowlet switching","author":"vanini","year":"2017","journal-title":"Proc USENIX NSDI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref19","article-title":"Reward Constrained Policy Optimization","author":"tessler","year":"2018","journal-title":"CoRR"},{"key":"ref4","article-title":"RILNET: A Reinforcement Learning Based Load Balancing Approach for Datacenter Networks","author":"lin","year":"2018","journal-title":"Machine Learning for Networking"},{"key":"ref3","first-page":"6379","article-title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2713168.2713193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12331-3_2"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2992"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2008.4483669"},{"key":"ref9","first-page":"1587","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1005686.1005697"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485954"},{"key":"ref21","article-title":"Amust framework-adaptive multimedia streaming simulation framework for ns-3 and ndnsim","author":"kreuzberger","year":"2016"},{"key":"ref24","article-title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","author":"rashid","year":"2018","journal-title":"Proc of ICML"},{"key":"ref23","first-page":"7265","article-title":"Learning Attentional Communication for Multi-Agent Cooperation","author":"jiang","year":"2018","journal-title":"Advances in Neural Information Processing Systems NeurIPS 2018"}],"event":{"name":"2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2022,1,8]]},"end":{"date-parts":[[2022,1,11]]}},"container-title":["2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9700484\/9700495\/09700657.pdf?arnumber=9700657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T21:15:08Z","timestamp":1655154908000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9700657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,8]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ccnc49033.2022.9700657","relation":{},"subject":[],"published":{"date-parts":[[2022,1,8]]}}}