{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:16:09Z","timestamp":1780607769189,"version":"3.54.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ontario Research Fund - Research Excellence Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2021,10,1]]},"DOI":"10.1109\/tkde.2020.2969419","type":"journal-article","created":{"date-parts":[[2020,1,24]],"date-time":"2020-01-24T22:30:20Z","timestamp":1579905020000},"page":"3394-3409","source":"Crossref","is-referenced-by-count":5,"title":["Paywall Policy Learning in Digital News Media"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9603-9625","authenticated-orcid":false,"given":"Heidar","family":"Davoudi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6990-9544","authenticated-orcid":false,"given":"Zana","family":"Rashidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1765-5751","authenticated-orcid":false,"given":"Aijun","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1144-7364","authenticated-orcid":false,"given":"Morteza","family":"Zihayat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2143-373X","authenticated-orcid":false,"given":"Gordon","family":"Edall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8621910"},{"key":"ref31","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref30","article-title":"Stable baselines","author":"hill","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref13","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Proc 14th Int Conf Neural Inf Process Syst"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref15","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645724"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/21670811.2016.1246373"},{"key":"ref27","first-page":"1075","article-title":"Analysis of temporal-diffference learning with function approximation","author":"tsitsiklis","year":"1997","journal-title":"Proc 9th Int Conf Neural Inf Process"},{"key":"ref3","article-title":"Reuters institute digital news report 2017","author":"newman","year":"0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1207\/s15327736me1802_4"},{"key":"ref29","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/17512786.2014.882056"},{"key":"ref8","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974973.16"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219892"},{"key":"ref9","first-page":"1265","article-title":"An MDP-based recommender system","volume":"6","author":"shani","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref1","article-title":"Paying for digital news: The rapid adoption and current landscape of digital subscriptions at US newspapers","author":"williams","year":"2016"},{"key":"ref20","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098061"},{"key":"ref21","first-page":"6351","article-title":"Learning combinatorial optimization algorithms over graphs","author":"dai","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3150-7_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/9781118029176"},{"key":"ref26","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/9534887\/08968338.pdf?arnumber=8968338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:49Z","timestamp":1652194249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,1]]},"references-count":34,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2020.2969419","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,1]]}}}