{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T12:53:15Z","timestamp":1772369595591,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/infocomwkshps50562.2020.9162925","type":"proceedings-article","created":{"date-parts":[[2020,8,10]],"date-time":"2020-08-10T21:55:09Z","timestamp":1597096509000},"page":"1248-1253","source":"Crossref","is-referenced-by-count":25,"title":["Deep Reinforcement Learning based Wireless Network Optimization: A Comparative Study"],"prefix":"10.1109","author":[{"given":"Kun","family":"Yang","sequence":"first","affiliation":[]},{"given":"Cong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Tie","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2885790"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2848295"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2893168"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918838"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2798164"},{"key":"ref15","first-page":"1","article-title":"Multi-agent reinforcement learning based resource allocation for UAV networks","author":"cui","year":"2019","journal-title":"IEEE Trans Wireless Commun"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872440"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933893"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref27","author":"schaul","year":"2015","journal-title":"Prioritized experience replay"},{"key":"ref3","first-page":"3230","article-title":"Efficient communication in multiagent reinforcement learning via variance based control","author":"zhang","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070409"},{"key":"ref5","author":"sutton","year":"2015","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646686"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2887282"},{"key":"ref2","first-page":"2827","article-title":"Neural episodic control","author":"pritzel","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref1","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref22","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"0","journal-title":"ICLRE"},{"key":"ref21","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proceedings of the 31st International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2921159"},{"key":"ref23","author":"blundell","year":"2016","journal-title":"Model-Free Episodic Control"},{"key":"ref26","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8648056"}],"event":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","location":"Toronto, ON, Canada","start":{"date-parts":[[2020,7,6]]},"end":{"date-parts":[[2020,7,9]]}},"container-title":["IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9146478\/9162584\/09162925.pdf?arnumber=9162925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:58:27Z","timestamp":1656453507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9162925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/infocomwkshps50562.2020.9162925","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}