{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:31:18Z","timestamp":1778347878143,"version":"3.51.4"},"reference-count":9,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Wireless Commun. Lett."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/lwc.2020.3035898","type":"journal-article","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T20:43:58Z","timestamp":1604522638000},"page":"508-511","source":"Crossref","is-referenced-by-count":39,"title":["Power Optimization in Device-to-Device Communications: A Deep Reinforcement Learning Approach With Dynamic Reward"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3081-1360","authenticated-orcid":false,"given":"Zelin","family":"Ji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adnan K.","family":"Kiani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8507-3975","authenticated-orcid":false,"given":"Zhijin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-7895","authenticated-orcid":false,"given":"Rizwan","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2014.2326852"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2016.2614507"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800601"},{"key":"ref8","author":"yang","year":"2020","journal-title":"Reconfigurable intelligent surface empowered underlaying device-to-device communication"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2957798"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2880956"},{"key":"ref9","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6807946"}],"container-title":["IEEE Wireless Communications Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962382\/9373029\/09247965.pdf?arnumber=9247965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:53Z","timestamp":1652194373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9247965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":9,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lwc.2020.3035898","relation":{},"ISSN":["2162-2337","2162-2345"],"issn-type":[{"value":"2162-2337","type":"print"},{"value":"2162-2345","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}