{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:18:47Z","timestamp":1743092327185,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031333798"},{"type":"electronic","value":"9783031333804"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-33380-4_31","type":"book-chapter","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T08:05:58Z","timestamp":1685088358000},"page":"400-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RLMixer: A Reinforcement Learning Approach for\u00a0Integrated Ranking with\u00a0Contrastive User Preference Modeling"],"prefix":"10.1007","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengchen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiming","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Carbonell, J., Goldstein, J.: The use of mmr, diversity-based reranking for reordering documents and producing summaries. In: Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 335\u2013336 (1998)","DOI":"10.1145\/290941.291025"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Chen, M., Beutel, A., Covington, P., Jain, S., Belletti, F., Chi, E.H.: Top-k off-policy correction for a reinforce recommender system. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. pp. 456\u2013464 (2019)","DOI":"10.1145\/3289600.3290999"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Fu, M., Agrawal, A., Irissappane, A.A., Zhang, J., Huang, L., Qu, H.: Deep reinforcement learning framework for category-based item recommendation. IEEE Transactions on Cybernetics (2021)","DOI":"10.1109\/TCYB.2021.3089941"},{"key":"31_CR4","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning, pp. 2052\u20132062 (2019)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Geyik, S.C., Ambler, S., Kenthapadi, K.: Fairness-aware ranking in search & recommendation systems with application to linkedin talent search. In: Proceedings of the 25th acm sigkdd international conference on knowledge discovery & data mining, pp. 2221\u20132231 (2019)","DOI":"10.1145\/3292500.3330691"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Guanjie, Z., et al.: Drn: A deep reinforcement learning framework for news recommendation. In: Proceedings of the 2018 World Wide Web Conference, pp. 167\u2013176 (2018)","DOI":"10.1145\/3178876.3185994"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Koutsopoulos, I.: Optimal advertisement allocation in online social media feeds. In: Proceedings of the 8th ACM International Workshop on Hot Topics in Planet-Scale Mobile Computing and Online Social Networking, pp. 43\u201348 (2016)","DOI":"10.1145\/2944789.2944791"},{"key":"31_CR8","unstructured":"Kumar, A., Fu, J., Soh, M., Tucker, G., Levine, S.: Stabilizing off-policy q-learning via bootstrapping error reduction. In: Advances in Neural Information Processing Systems, pp. 11761\u201311771 (2019)"},{"key":"31_CR9","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 1179\u20131191 (2020)"},{"key":"31_CR10","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Liao, G., et al.: Cross dqn: Cross deep q network for ads allocation in feed. arXiv preprint arXiv:2109.04353 (2021)","DOI":"10.1145\/3485447.3512109"},{"key":"31_CR12","unstructured":"Matsushima, T., Furuta, H., Matsuo, Y., Nachum, O., Gu, S.S.: Deployment-efficient reinforcement learning via model-based offline optimization. In: International Conference on Learning Representations (2021)"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Pei, C., et al.: Personalized re-ranking for recommendation. In: Proceedings of the 13th ACM Conference on Recommender Systems, pp. 3\u201311 (2019)","DOI":"10.1145\/3298689.3347000"},{"key":"31_CR14","unstructured":"Wu, Y., Tucker, G., Nachum, O.: Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361 (2019)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Xiao, T., Wang, D.: A general offline reinforcement learning framework for interactive recommendation. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i5.16579"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Yan, J., Xu, Z., Tiwana, B., Chatterjee, S.: Ads allocation in feed via constrained optimization. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3386\u20133394 (2020)","DOI":"10.1145\/3394486.3403391"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, M., Li, Z., Bo, A., Haifeng, L., Yifan, Y., Chen, C.: Impression allocation for combating fraud in e-commerce via deep reinforcement learning with action norm penalty. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 3940\u20133946 (2018)","DOI":"10.24963\/ijcai.2018\/548"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, X., Gu, C., Zhang, H., Yang, X., Liu, X., Tang, J., Liu, H.: Dear: Deep reinforcement learning for online advertising impression in recommender systems. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp. 750\u2013758 (2021)","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, G., et al.: Deep interest evolution network for click-through rate prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 5941\u20135948 (2019)","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, G., et al.: Deep interest network for click-through rate prediction. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1059\u20131068 (2018)","DOI":"10.1145\/3219819.3219823"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33380-4_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T04:35:59Z","timestamp":1729485359000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33380-4_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031333798","9783031333804"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33380-4_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Osaka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"813","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"143","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}