{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:47:49Z","timestamp":1776275269635,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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":[[2021,11,1]]},"DOI":"10.1109\/icnp52444.2021.9651934","type":"proceedings-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:32:43Z","timestamp":1640727163000},"page":"1-11","source":"Crossref","is-referenced-by-count":17,"title":["Constraint-Aware Deep Reinforcement Learning for End-to-End Resource Orchestration in Mobile Networks"],"prefix":"10.1109","author":[{"given":"Qiang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Nakjung","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Han","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737488"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3397166.3409133"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1355734.1355746"},{"key":"ref32","first-page":"8","article-title":"Nvidia CUDA C programming guide","volume":"120","author":"nvidia","year":"2011","journal-title":"NVIDIA Corporation"},{"key":"ref31","article-title":"Openair-cn repository","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WoWMoM.2014.6918985"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737517"},{"key":"ref36","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3161413"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345431"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP49622.2020.9259378"},{"key":"ref11","year":"2020","journal-title":"O-RAN-WG1-O-RAN Architecture Description - v01 00 00"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref13","article-title":"Theory and application of reward shaping in reinforcement learning","author":"laud","year":"2004","journal-title":"Tech Rep"},{"key":"ref14","article-title":"ETSI Zero touch network & Service Management (ZSM)","year":"0"},{"key":"ref15","article-title":"3GPP TR 28.801, Study on management and orchestration of network slicing for next generation network","year":"2018","journal-title":"3GPP Tech Rep"},{"key":"ref16","article-title":"ETSI 5G Management and orchestration, 5G Network Resource Model (NRM), v15.0.0","year":"2018","journal-title":"ETSI Tech Rep"},{"key":"ref17","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref18","year":"2019","journal-title":"Generic Network Slice Template V2 0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref28","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600935"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600951"},{"key":"ref6","article-title":"Management and orchestration, Architecture framework","year":"2020","journal-title":"3rd Generation Partnership Project (3GPP) Technical Specification"},{"key":"ref29","article-title":"OpenAirInterface repository","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3281411.3281435"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419186"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00028"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2815638"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref1","article-title":"Minimum requirements related to technical performance for IMT-2020 radio interface (s)","year":"2017"},{"key":"ref20","first-page":"7553","article-title":"Constrained reinforcement learning has zero duality gap","author":"paternain","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018"},{"key":"ref21","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref26","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241567"}],"event":{"name":"2021 IEEE 29th International Conference on Network Protocols (ICNP)","location":"Dallas, TX, USA","start":{"date-parts":[[2021,11,1]]},"end":{"date-parts":[[2021,11,5]]}},"container-title":["2021 IEEE 29th International Conference on Network Protocols (ICNP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9651731\/9651908\/09651934.pdf?arnumber=9651934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T17:00:05Z","timestamp":1652202005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9651934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icnp52444.2021.9651934","relation":{},"subject":[],"published":{"date-parts":[[2021,11,1]]}}}