{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:06:32Z","timestamp":1777406792004,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"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":[[2021,3,3]]},"DOI":"10.1109\/csicc52343.2021.9420615","type":"proceedings-article","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T08:37:26Z","timestamp":1620463046000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Improving ranking function and diversification in interactive recommendation systems based on deep reinforcement learning"],"prefix":"10.1109","author":[{"given":"Vahid","family":"Baghi","sequence":"first","affiliation":[{"name":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seyed Mohammad","family":"Seyed Motehayeri","sequence":"additional","affiliation":[{"name":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Moeini","sequence":"additional","affiliation":[{"name":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rooholah","family":"Abedian","sequence":"additional","affiliation":[{"name":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015"},{"key":"ref32","article-title":"Diversity-promoting deep reinforcement learning for interactive recommendation","author":"liu","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106196"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052585"},{"key":"ref37","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref36","first-page":"1257","article-title":"Probabilistic matrix factorization","author":"mnih","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2019.02.006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68474-1_3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref11","article-title":"A short survey on memory based reinforcement learning","author":"ramani","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1363686.1363954"},{"key":"ref13","first-page":"1265","article-title":"An mdp-based recommender system","volume":"6","author":"shani","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref15","article-title":"Deep reinforcement learning based recommendation with explicit user-item interactions modeling","author":"liu","year":"2018"},{"key":"ref16","article-title":"Deep reinforcement learning for list-wise recommendations","author":"zhao","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Annoy","year":"0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487636"},{"key":"ref4","first-page":"1297","article-title":"Efficient thompson sampling for online matrix-factorization recommendation","author":"kawale","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835486"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505690"},{"key":"ref6","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.024"},{"key":"ref5","first-page":"2695","article-title":"Factorization bandits for interactive recommendation","volume":"17","author":"wang","year":"2017","journal-title":"AAAI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1145\/1772690.1772758","article-title":"A contextual-bandit approach to personalized news article recommendation","author":"li","year":"2010","journal-title":"Proceedings of the 19th International Conference on World Wide Web"},{"key":"ref9","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018"},{"key":"ref1","first-page":"2249","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSACW.2013.68"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219846"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060754"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1454008.1454030"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11768012_6"}],"event":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","location":"Tehran, Iran","start":{"date-parts":[[2021,3,3]]},"end":{"date-parts":[[2021,3,4]]}},"container-title":["2021 26th International Computer Conference, Computer Society of Iran (CSICC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9420464\/9420539\/09420615.pdf?arnumber=9420615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:17:45Z","timestamp":1659485865000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9420615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,3]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/csicc52343.2021.9420615","relation":{},"subject":[],"published":{"date-parts":[[2021,3,3]]}}}