{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T15:59:43Z","timestamp":1784995183955,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2017YFB1301003"],"award-info":[{"award-number":["2017YFB1301003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701439"],"award-info":[{"award-number":["61701439"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61731002"],"award-info":[{"award-number":["61731002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Key Research and Development Plan","award":["2019C01002"],"award-info":[{"award-number":["2019C01002"]}]},{"name":"Zhejiang Key Research and Development Plan","award":["2019C03131"],"award-info":[{"award-number":["2019C03131"]}]},{"name":"Zhejiang Lab","award":["2019LC0AB01"],"award-info":[{"award-number":["2019LC0AB01"]}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY20F010016"],"award-info":[{"award-number":["LY20F010016"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2019QNA5010"],"award-info":[{"award-number":["2019QNA5010"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/jsac.2019.2959185","type":"journal-article","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T20:38:21Z","timestamp":1576183101000},"page":"334-349","source":"Crossref","is-referenced-by-count":222,"title":["GAN-Powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicing"],"prefix":"10.1109","volume":"38","author":[{"given":"Yuxiu","family":"Hua","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5485-4955","authenticated-orcid":false,"given":"Xianfu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1492-1364","authenticated-orcid":false,"given":"Honggang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"},{"key":"ref38","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref33","article-title":"GAN Q-learning","author":"doan","year":"2018","journal-title":"arXiv 1805 04874"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700246"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.123"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2922961"},{"key":"ref35","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv 1511 06581"},{"key":"ref34","article-title":"Distributional multivariate policy evaluation and exploration with the Bellman GAN","author":"freirich","year":"2019","journal-title":"Proc ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600935"},{"key":"ref40","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"arXiv 1804 08617"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EuCNC.2016.7561023"},{"key":"ref12","year":"2016","journal-title":"Study on New Services and Markets Technology Enables Release 14"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881964"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600939"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2846543"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2842189"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761841"},{"key":"ref18","first-page":"1","article-title":"Network slicing management & prioritization in 5G mobile systems","author":"jiang","year":"2016","journal-title":"Proc Eur Wireless Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2878965"},{"key":"ref28","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600951"},{"key":"ref27","article-title":"Implicit quantile networks for distributional reinforcement learning","author":"dabney","year":"2018","journal-title":"arXiv 1806 06923"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600304WC"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7509393"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831240"},{"key":"ref5","year":"2017","journal-title":"Minimum Requirement Related to Technical Performance for IMT-2020 Radio Interface (s)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2815638"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2017.3481355"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600936"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600940"},{"key":"ref1","article-title":"GAN-based deep distributional reinforcement learning for resource management in network slicing","author":"hua","year":"2019","journal-title":"Proc Globecom"},{"key":"ref46","article-title":"Which training methods for GANs do actually converge?","author":"mescheder","year":"2018","journal-title":"arXiv 1801 04406"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2018.2814022"},{"key":"ref45","year":"2019","journal-title":"Network Slicing Architecture"},{"key":"ref48","year":"2017","journal-title":"Service Requirements for Next Generation New Services Markets Release 15"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref47","year":"2010","journal-title":"Evolved universal terrestrial radio access (E-UTRA) further advancements for E-UTRA physical layer aspects Release 9"},{"key":"ref21","volume":"37","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref42","first-page":"5767","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref24","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proc ICML"},{"key":"ref41","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref23","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"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2018.8319321"},{"key":"ref26","first-page":"2892","article-title":"Distributional reinforcement learning with quantile regression","author":"dabney","year":"2018","journal-title":"Proc AAAI"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2018.8319259"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1257\/jep.15.4.143"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9007054\/08931561.pdf?arnumber=8931561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:22:34Z","timestamp":1651069354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8931561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2019.2959185","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}