{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:19:25Z","timestamp":1759335565363,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"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":[[2021,6,15]]},"DOI":"10.1109\/medcomnet52149.2021.9501279","type":"proceedings-article","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T22:24:38Z","timestamp":1628547878000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["A Multi-Agent Reinforcement Learning Architecture for Network Slicing Orchestration"],"prefix":"10.1109","author":[{"given":"Federico","family":"Mason","sequence":"first","affiliation":[]},{"given":"Gianfranco","family":"Nencioni","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Zanella","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","year":"2011","author":"boyd","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2869964"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2979667"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.9.000D19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904371"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345431"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2986050"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2815638"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2720668"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2894305"},{"key":"ref7","article-title":"Re-inforcement learning through asynchronous advantage actor-critic on a GPU","author":"babaeizadeh","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2872781"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486303"},{"journal-title":"3rd Generation Partnership Project (3GPP) Technical Specification (TS) 22 368","article-title":"Service requirements for next generation new services and markets","year":"2020","key":"ref1"},{"key":"ref20","article-title":"Intelligent resource slicing for eMBB and URLLC coexistence in 5G and beyond: A deep reinforcement learning based approach","author":"alsenwi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-6772-4_76"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177011137"},{"key":"ref23","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","author":"jaakkola","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"journal-title":"3rd Generation Partnership Project (3GPP) Technical Specification (TS) 23 682 03","article-title":"System architecture for the 5G System (5GS)","year":"2020","key":"ref25"}],"event":{"name":"2021 19th Mediterranean Communication and Computer Networking Conference (MedComNet)","start":{"date-parts":[[2021,6,15]]},"location":"Ibiza, Spain","end":{"date-parts":[[2021,6,17]]}},"container-title":["2021 19th Mediterranean Communication and Computer Networking Conference (MedComNet)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9501230\/9501231\/09501279.pdf?arnumber=9501279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:43:49Z","timestamp":1652197429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9501279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,15]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/medcomnet52149.2021.9501279","relation":{},"subject":[],"published":{"date-parts":[[2021,6,15]]}}}