{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:18Z","timestamp":1740169218435,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806132","61801304"],"award-info":[{"award-number":["61806132","61801304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009019","name":"Guangdong NSF","doi-asserted-by":"publisher","award":["2020A1515010741"],"award-info":[{"award-number":["2020A1515010741"]}],"id":[{"id":"10.13039\/501100009019","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009019","name":"Tencent Rhino-Bird Young Faculty Open Fund and the Priming Research Fund in Shenzhen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009019","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3014791","type":"journal-article","created":{"date-parts":[[2020,8,6]],"date-time":"2020-08-06T20:45:29Z","timestamp":1596746729000},"page":"145006-145017","source":"Crossref","is-referenced-by-count":5,"title":["Deep Reinforcement Learning-Based Access Control for Buffer-Aided Relaying Systems With Energy Harvesting"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8470-7246","authenticated-orcid":false,"given":"Haodi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3306-9317","authenticated-orcid":false,"given":"Chen Jason","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2216-0737","authenticated-orcid":false,"given":"Kaishun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0541-0298","authenticated-orcid":false,"given":"Sheng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref32","first-page":"1640","article-title":"Knowledge transfer for deep reinforcement learning with hierarchical experience replay","author":"yin","year":"2017","journal-title":"Proc AAAI"},{"key":"ref31","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc NIPS"},{"key":"ref30","first-page":"1553","article-title":"A deep hierarchical approach to lifelong learning in Minecraft","author":"tessler","year":"2017","journal-title":"Proc AAAI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2635142"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2773526"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110921"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2545418"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511405"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2703855"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422710"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.030413.121120"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/s20010044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2018.2801725"},{"key":"ref28","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2647250"},{"key":"ref27","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.130816"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7081085"},{"key":"ref29","first-page":"2923","article-title":"Hierarchical imitation and reinforcement learning","author":"le","year":"2018","journal-title":"Proc ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2391531"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2950070"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2901734"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2438296"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.012314.121185"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2004.1341264"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2610444"},{"key":"ref22","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WCNCW.2017.7919075"},{"key":"ref24","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp"},{"key":"ref25","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn (ICML)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09161419.pdf?arnumber=9161419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:56:43Z","timestamp":1642003003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9161419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3014791","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}