{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:20:55Z","timestamp":1792786855173,"version":"4.5.0"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2020M673182"],"award-info":[{"award-number":["2020M673182"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976043"],"award-info":[{"award-number":["61976043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0100202"],"award-info":[{"award-number":["2018AAA0100202"]}]},{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","award":["0015\/2019\/AKP"],"award-info":[{"award-number":["0015\/2019\/AKP"]}],"id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2019YFB2102100"],"award-info":[{"award-number":["2019YFB2102100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tii.2022.3209290","type":"journal-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T16:45:15Z","timestamp":1664210715000},"page":"2049-2061","source":"Crossref","is-referenced-by-count":26,"title":["A Deep Reinforcement Learning Recommender System With Multiple Policies for Recommendations"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9257-126X","authenticated-orcid":false,"given":"Mingsheng","family":"Fu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7590-144X","authenticated-orcid":false,"given":"Liwei","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6396-8172","authenticated-orcid":false,"given":"Ananya","family":"Rao","sequence":"additional","affiliation":[{"name":"School of Engineering and Technology, University of Washington, Tacoma, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athirai A.","family":"Irissappane","sequence":"additional","affiliation":[{"name":"School of Engineering and Technology, University of Washington, Tacoma, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6114-3441","authenticated-orcid":false,"given":"Hong","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330859"},{"key":"ref11","first-page":"1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc NIPS DEEP Learn Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref14","first-page":"1","article-title":"Session-based recommendations with recurrent neural networks","author":"hidasi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331302"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412044"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3359554"},{"key":"ref4","first-page":"452","article-title":"BPR: Bayesian personalized ranking from implicit feedback","author":"rendle","year":"0","journal-title":"Proc 25th Conf Uncertainty Artif Intell"},{"key":"ref27","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2937547"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00122"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401181"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2947066"},{"key":"ref9","first-page":"1","article-title":"Varibad: A very good method for bayes-adaptive deep rl via meta-learning","author":"zintgraf","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2893714"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/360"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"ref24","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401170"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412044"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/9989328\/09903322.pdf?arnumber=9903322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T14:19:32Z","timestamp":1673878772000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9903322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":28,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tii.2022.3209290","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}