{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:39:07Z","timestamp":1730266747964,"version":"3.28.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650400","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Offline Reinforcement Learning for Sequential Recommendation from A Pair-Wise Q-Learning Perspective"],"prefix":"10.1109","author":[{"given":"Runqi","family":"Yang","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaohui","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Likang","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning","author":"Fujimoto"},{"article-title":"Offline reinforcement learning with implicit Q-Learning","year":"2021","author":"Kostrikov","key":"ref4"},{"key":"ref5","first-page":"1179","article-title":"Conservative Q-Learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Bpr: Bayesian personalized ranking from implicit feedback","year":"2012","author":"Rendle","key":"ref6"},{"issue":"9","key":"ref7","article-title":"An mdp-based recommender system","volume":"6","author":"Shani","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-2490-1_27"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00074"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0030"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/41703509"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2005.115"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/489"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handbooks in operations research and management science"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401134"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"article-title":"Where you like to go next: Successive point-of-interest recommendation","volume-title":"Twenty-Third international joint conference on Artificial Intelligence","author":"Cheng","key":"ref22"},{"key":"ref23","first-page":"81","article-title":"Implicit feedback for recommender systems","volume-title":"Proceedings of the AAAI workshop on recommender systems","volume":"83","author":"Oard"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/69.842255"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30672-3_19"},{"article-title":"Session-based recommendations with recurrent neural networks","year":"2015","author":"Hidasi","key":"ref26"},{"article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","year":"2014","author":"Chung","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271761"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498494"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref41","article-title":"A model-based reinforcement learning with adversarial training for online recommendation","volume":"32","author":"Bai","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"},{"key":"ref43","first-page":"1052","article-title":"Generative adversarial user model for reinforcement learning based recommendation system","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531714"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462978"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482448"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16579"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531796"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"article-title":"Automatic differentiation in pytorch","year":"2017","author":"Paszke","key":"ref51"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650400.pdf?arnumber=10650400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:18:13Z","timestamp":1725945493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650400","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}