{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:52:09Z","timestamp":1770339129528,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"General Program and Major Project of Shenzhen Science and Technology Research and Development Fund","award":["JCYJ20220530164813029"],"award-info":[{"award-number":["JCYJ20220530164813029"]}]},{"name":"General Program and Major Project of Shenzhen Science and Technology Research and Development Fund","award":["KJZD20230923113800002"],"award-info":[{"award-number":["KJZD20230923113800002"]}]},{"DOI":"10.13039\/501100010822","name":"Chengdu Science and Technology Bureau","doi-asserted-by":"publisher","award":["2023-CY02-00003-GX"],"award-info":[{"award-number":["2023-CY02-00003-GX"]}],"id":[{"id":"10.13039\/501100010822","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tkde.2024.3402649","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:32:06Z","timestamp":1716226326000},"page":"5753-5767","source":"Crossref","is-referenced-by-count":2,"title":["CIPPO: Contrastive Imitation Proximal Policy Optimization for Recommendation Based on Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2202-601X","authenticated-orcid":false,"given":"Weilong","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9214-261X","authenticated-orcid":false,"given":"Shaoliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"WeChat Search Application Department, Tencent, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-5647","authenticated-orcid":false,"given":"Ruobing","family":"Xie","sequence":"additional","affiliation":[{"name":"WeChat Search Application Department, Tencent, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5279-9908","authenticated-orcid":false,"given":"Feng","family":"Xia","sequence":"additional","affiliation":[{"name":"WeChat Search Application Department, Tencent, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5471-500X","authenticated-orcid":false,"given":"Leyu","family":"Lin","sequence":"additional","affiliation":[{"name":"WeChat Search Application Department, Tencent, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9250-8711","authenticated-orcid":false,"given":"Xinran","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1083-8865","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-2150","authenticated-orcid":false,"given":"Yanru","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/360"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16580"},{"key":"ref6","first-page":"5426","article-title":"Policy learning for fairness in ranking","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Singh"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481917"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16521"},{"key":"ref9","article-title":"Improving long-term metrics in recommendation systems using short-horizon offline RL","author":"Mazoure","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539040"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21424"},{"key":"ref12","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref13","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref14","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref15","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref16","article-title":"RecoGym: A reinforcement learning environment for the problem of product recommendation in online advertising","author":"Rohde","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"ref18","article-title":"RecSim: A configurable simulation platform for recommender systems","author":"Ie","year":"2019"},{"key":"ref19","article-title":"The challenges of exploration for offline reinforcement learning","author":"Lambert","year":"2022"},{"key":"ref20","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/00220670209598786"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5768"},{"key":"ref27","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref28","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda"},{"key":"ref29","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref31","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00103"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref34","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"Jaques","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080677"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914798"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412044"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref45","first-page":"941","article-title":"Learning action representations for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chandak"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"ref49","first-page":"171","article-title":"On the design of consequential ranking algorithms","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Tabibian"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498494"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546758"},{"key":"ref52","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Munos"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474247"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref56","article-title":"Truncated horizon policy search: Combining reinforcement learning & imitation learning","author":"Sun","year":"2018"},{"key":"ref57","article-title":"Fast policy learning through imitation and reinforcement","author":"Cheng","year":"2018"},{"key":"ref58","article-title":"Trust the model when it is confident: Masked model-based actor-critic","author":"Pan","year":"2020"},{"key":"ref59","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481952"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref62","first-page":"971","article-title":"Self-normalizing neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Klambauer"},{"key":"ref63","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591648"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref66","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref67","first-page":"802","article-title":"Coupled group lasso for web-scale CTR prediction in display advertising","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yan"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911537"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10709365\/10534824.pdf?arnumber=10534824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T05:41:22Z","timestamp":1728452482000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10534824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":68,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3402649","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":[[2024,11]]}}}