{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T08:37:32Z","timestamp":1773304652788,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"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":["42171404"],"award-info":[{"award-number":["42171404"]}],"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":["62271352"],"award-info":[{"award-number":["62271352"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Interdisciplinary Key Project of Tongji University","award":["2023-2-ZD-04"],"award-info":[{"award-number":["2023-2-ZD-04"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["22120230441"],"award-info":[{"award-number":["22120230441"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Engineering Research Center for Blockchain Applications and Services","award":["19DZ2255100"],"award-info":[{"award-number":["19DZ2255100"]}]},{"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 Internet Things J."],"published-print":{"date-parts":[[2024,5,1]]},"DOI":"10.1109\/jiot.2023.3347279","type":"journal-article","created":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T19:32:08Z","timestamp":1703619128000},"page":"15359-15374","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement-Learning-Based Policy Design for Outage Minimization in DF Relaying Networks"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5865-2314","authenticated-orcid":false,"given":"Yuanzhe","family":"Geng","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2706-6208","authenticated-orcid":false,"given":"Erwu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2974-0972","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering and the Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7965-5071","authenticated-orcid":false,"given":"Pengcheng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7742-3026","authenticated-orcid":false,"given":"Binyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6623-9722","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3007869"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC51323.2021.9498857"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3249227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2865408"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3133298"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRD.2016.2544801"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3017391"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2907252"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3068225"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3083062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3088672"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000835"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3174469"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2980198"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3095161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040957"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC57344.2023.10099349"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2789466"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3244909"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3123959"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3008178"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/BalkanCom58402.2023.10167871"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838967"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3051239"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2985873"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3094465"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2022.3154292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3119689"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3103810"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3203028"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087225"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2958814"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.3020850"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2014.2377129"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2951416"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417498"},{"key":"ref40","first-page":"1","article-title":"Robust reinforcement learning for continuous control with model misspecification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mankowitz"},{"key":"ref41","first-page":"4951","article-title":"Monotonic robust policy optimization with model discrepancy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref42","first-page":"22547","article-title":"Efficient adversarial training without attacking: Worst-case-aware robust reinforcement learning","volume":"35","author":"Liang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/430"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070206"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879486"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2925719"},{"key":"ref48","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref49","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3121281"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2921159"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10508620\/10374206.pdf?arnumber=10374206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T19:01:47Z","timestamp":1714762907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10374206\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,1]]},"references-count":51,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3347279","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,1]]}}}