{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:21:54Z","timestamp":1740100914927,"version":"3.37.3"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/vtc2022-spring54318.2022.9860594","type":"proceedings-article","created":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T19:39:23Z","timestamp":1661456363000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ju-Hyung","family":"Lee","sequence":"first","affiliation":[{"name":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyowoon","family":"Seo","sequence":"additional","affiliation":[{"name":"Kwangwoon University,Department of Electronics and Communications Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihong","family":"Park","sequence":"additional","affiliation":[{"name":"Deakin University,School of Information Technology,Geelong,VIC,Australia,3220"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Bennis","sequence":"additional","affiliation":[{"name":"University of Oulu,Centre for Wireless Communications,Oulu,Finland,90014"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young-Chai","family":"Ko","sequence":"additional","affiliation":[{"name":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joongheon","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"4294","article-title":"Learning values across many orders of magnitude","author":"van hasselt","year":"2016"},{"key":"ref11","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"1999","journal-title":"ser Proc of International Conf on Neural Information Processing (NIPS)"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proc Int'l Conf Machine Learning (ICML '05)"},{"year":"2021","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095828"},{"journal-title":"Medium Access Control (MAC) protocol specification","year":"2021","key":"ref15"},{"key":"ref4","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"in Proc of International Conf on Neural Information Processing (NIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps52748.2021.9681991"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9348105"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2688328"},{"key":"ref8","first-page":"1146","article-title":"Stabilising experience replay for deep Multi-Agent reinforcement learning","volume":"70","author":"foerster","year":"2017","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"journal-title":"Pointing system performance analysis for optical inter-satellite communication on CubeSats Massachusetts Institute of Technology (MIT)","year":"2017","author":"yoon","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3080677"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2021.3093110"},{"key":"ref9","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"}],"event":{"name":"2022 IEEE 95th Vehicular Technology Conference (VTC2022-Spring)","start":{"date-parts":[[2022,6,19]]},"location":"Helsinki, Finland","end":{"date-parts":[[2022,6,22]]}},"container-title":["2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9860273\/9860350\/09860594.pdf?arnumber=9860594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:21:44Z","timestamp":1663618904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9860594\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/vtc2022-spring54318.2022.9860594","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}