{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:18:16Z","timestamp":1774595896586,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171280"],"award-info":[{"award-number":["62171280"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tnet.2023.3342837","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:13:05Z","timestamp":1702930385000},"page":"2159-2173","source":"Crossref","is-referenced-by-count":8,"title":["Deep Reinforcement Learning Based Cross-Layer Design in Terahertz Mesh Backhaul Networks"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5158-2632","authenticated-orcid":false,"given":"Zhifeng","family":"Hu","sequence":"first","affiliation":[{"name":"Terahertz Wireless Communications (TWC) Laboratory, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9638-4736","authenticated-orcid":false,"given":"Chong","family":"Han","sequence":"additional","affiliation":[{"name":"Terahertz Wireless Communications (TWC) Laboratory and the Department of Electronic Engineering and Cooperative Medianet Innovation Center (CMIC), Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1353-1420","authenticated-orcid":false,"given":"Xudong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Michigan–Shanghai Jiao Tong University (UM-SJTU) Joint Institute, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2699183"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2883465"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3052370"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3149213"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3118958"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109533"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3148203"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000690"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700890"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3171800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-022-00897-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC47757.2020.9049790"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3138791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2921563"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900346"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2005.1509968"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC45663.2020.9120546"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2886897"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.nancom.2018.12.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2016.7503795"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2702158"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3120266"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS51825.2021.9484490"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2007.4300987"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2017.7962658"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2337060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070510"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2015.2440356"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2992628"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2019.8824971"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2316791"},{"key":"ref32","first-page":"1","article-title":"DAGs with NO TEARS: Continuous optimization for structure learning","volume-title":"Proc. NIPS","author":"Zheng"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref34","first-page":"11480","article-title":"CRPO: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"Proc. ICML","author":"Xu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20737"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041405"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3179811"},{"key":"ref38","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref39","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2009.2025703"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3136788"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/28869.28874"},{"key":"ref43","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref44","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. NIPS","author":"Sutton"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10559910\/10364873.pdf?arnumber=10364873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:43:47Z","timestamp":1719351827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2023.3342837","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}