{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:12:12Z","timestamp":1784131932395,"version":"3.55.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["42171404"],"award-info":[{"award-number":["42171404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61771345"],"award-info":[{"award-number":["61771345"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["19511102002"],"award-info":[{"award-number":["19511102002"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Innovation Action Plan Project","award":["21220713100"],"award-info":[{"award-number":["21220713100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1109\/tcomm.2021.3119689","type":"journal-article","created":{"date-parts":[[2021,10,14]],"date-time":"2021-10-14T01:22:25Z","timestamp":1634174545000},"page":"171-184","source":"Crossref","is-referenced-by-count":49,"title":["Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5865-2314","authenticated-orcid":false,"given":"Yuanzhe","family":"Geng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2706-6208","authenticated-orcid":false,"given":"Erwu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2974-0972","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1393-908X","authenticated-orcid":false,"given":"Yiming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2797914"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2687622"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2865408"},{"key":"ref5","article-title":"Beamforming and performance evaluation for intelligent reflecting surface aided wireless system with hardware impairments","volume-title":"arXiv:2006.00664","author":"Liu","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRD.2016.2544801"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm.2016.7778750"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2005.862417"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3017391"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2919024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2885807"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2020.2965116"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2944403"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2788562"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2496724"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2011.2121926"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2011.120611.11006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2907252"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2949129"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2913424"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3023458"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2370046"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2985873"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2925719"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3008178"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761525"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2011.2112786"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2005.846989"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2004.836447"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070206"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879486"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-020-01801-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref37","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Espeholt"},{"key":"ref38","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Mnih"},{"issue":"2","key":"ref39","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA, Neural Netw. Mach. Learn."},{"key":"ref40","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Kulkarni"},{"key":"ref41","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Nachum"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891792"},{"key":"ref43","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Wang"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/26\/9681827\/09568962.pdf?arnumber=9568962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:25:11Z","timestamp":1705015511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9568962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcomm.2021.3119689","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"value":"0090-6778","type":"print"},{"value":"1558-0857","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1]]}}}