{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:55:30Z","timestamp":1773377730102,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,26]],"date-time":"2022-06-26T00:00:00Z","timestamp":1656201600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,26]],"date-time":"2022-06-26T00:00:00Z","timestamp":1656201600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,26]]},"DOI":"10.1109\/isit50566.2022.9834756","type":"proceedings-article","created":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T15:34:22Z","timestamp":1659540862000},"page":"2684-2689","source":"Crossref","is-referenced-by-count":0,"title":["Simultaneous Sensing and Channel Access based on Partial Observations via Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yoel","family":"Bokobza","sequence":"first","affiliation":[{"name":"Ben-Gurion University of the Negev,Department of Electrical and Computer Engineering,Be’er-Sheva,Israel"}]},{"given":"Ron","family":"Dabora","sequence":"additional","affiliation":[{"name":"Ben-Gurion University of the Negev,Department of Electrical and Computer Engineering,Be’er-Sheva,Israel"}]},{"given":"Kobi","family":"Cohen","sequence":"additional","affiliation":[{"name":"Ben-Gurion University of the Negev,Department of Electrical and Computer Engineering,Be’er-Sheva,Israel"}]}],"member":"263","reference":[{"key":"ref10","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/dac.2338"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2048766"},{"key":"ref14","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":"ref15","first-page":"257","article-title":"Deep reinforcement learning for dynamic multichannel access","author":"wang","year":"2017","journal-title":"Proc International Conference on Computing Networking and Communications (ICNC)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DySPAN.2018.8610402"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2018.8599697"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2984227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2198613"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of the International Conference on Learning Representations ICLR 2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068950"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195522"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2230215"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2389620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2014.7094730"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2025561"},{"key":"ref9","article-title":"Distributed learning over Markovian fading channels for stable spectrum access","author":"gafni","year":"2021","journal-title":"arXiv preprint arXiv 2101 11517"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646405"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2981320"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2952909"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref23","first-page":"2613","article-title":"Double q-learning","volume":"23","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Deep reinforcement learning for simultaneous sensing and channel access in cognitive networks","author":"bokobza","year":"2021","journal-title":"submitted to the IEEE Transactions on Wireless Communications 2021 arXiv preprint reference arXiv 2110 14541v1"},{"key":"ref25","volume":"25","author":"nielsen","year":"2015","journal-title":"Neural Networks and Deep Learning"}],"event":{"name":"2022 IEEE International Symposium on Information Theory (ISIT)","location":"Espoo, Finland","start":{"date-parts":[[2022,6,26]]},"end":{"date-parts":[[2022,7,1]]}},"container-title":["2022 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9834325\/9834269\/09834756.pdf?arnumber=9834756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:35:00Z","timestamp":1773347700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9834756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,26]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/isit50566.2022.9834756","relation":{},"subject":[],"published":{"date-parts":[[2022,6,26]]}}}