{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:28:12Z","timestamp":1771705692011,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","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":"am","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"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-1811497"],"award-info":[{"award-number":["ECCS-1811497"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1937487"],"award-info":[{"award-number":["CCF-1937487"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/jiot.2020.2988268","type":"journal-article","created":{"date-parts":[[2020,4,16]],"date-time":"2020-04-16T20:48:47Z","timestamp":1587070127000},"page":"7517-7528","source":"Crossref","is-referenced-by-count":20,"title":["Accelerating Model-Free Reinforcement Learning With Imperfect Model Knowledge in Dynamic Spectrum Access"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1813-7764","authenticated-orcid":false,"given":"Lianjun","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1915-1784","authenticated-orcid":false,"given":"Lingjia","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-5280","authenticated-orcid":false,"given":"Jianan","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Hao-Hsuan","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7202-1095","authenticated-orcid":false,"given":"Jonathan D.","family":"Ashdown","sequence":"additional","affiliation":[]},{"given":"Jianzhong","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1354-0204","authenticated-orcid":false,"given":"Yang","family":"Yi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"buckman","year":"2018","journal-title":"Proc 32nd Int Conf Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6815890"},{"key":"ref12","author":"marek","year":"2019","journal-title":"Marek’s Take Dynamic Spectrum Sharing May Change the 5G Deployment Game"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.361604"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872441"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WPMC.2014.7014863"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254101"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/T-WC.2008.071349"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref8","first-page":"5694","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"racani\u00e8re","year":"2017","journal-title":"Proc 31st Int Conf Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref9","author":"feinberg","year":"2018","journal-title":"Model-based value estimation for efficient model-free reinforcement learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref20","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref22","article-title":"Broadband radio access networks (BRAN); 5 GHz high performance RLAN; harmonized EN covering the essential requirements of article 3.2 of the R&TTE directive, v1.7.2","year":"2014"},{"key":"ref21","author":"bertsekas","year":"1987","journal-title":"Dynamic Programming Deterministic and Stochastic Models"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070409"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2011.5982539"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6488907\/9165761\/9069218-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9165761\/09069218.pdf?arnumber=9069218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:28:55Z","timestamp":1651080535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9069218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":28,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2020.2988268","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}