{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T01:05:42Z","timestamp":1728176742302},"reference-count":11,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/pimrc48278.2020.9217216","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T19:58:06Z","timestamp":1602187086000},"source":"Crossref","is-referenced-by-count":4,"title":["Service-Driven Resource Management in Vehicular Networks Based on Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zhengwei","family":"Lyu","sequence":"first","affiliation":[]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Man","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yuanbin","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2900234"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WCNCW.2019.8902681"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1601150"},{"key":"ref11","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2816942"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2958261"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2013.6616115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890686"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2930601"}],"event":{"name":"2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications","location":"London, United Kingdom","start":{"date-parts":[[2020,8,31]]},"end":{"date-parts":[[2020,9,3]]}},"container-title":["2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210501\/9217048\/09217216.pdf?arnumber=9217216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:54:55Z","timestamp":1656453295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9217216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/pimrc48278.2020.9217216","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}