{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T18:43:42Z","timestamp":1762022622288,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030474256"},{"type":"electronic","value":"9783030474263"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-47426-3_2","type":"book-chapter","created":{"date-parts":[[2020,5,8]],"date-time":"2020-05-08T06:02:49Z","timestamp":1588917769000},"page":"16-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Off-Policy Recommendation System Without Exploration"],"prefix":"10.1007","author":[{"given":"Chengwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tengfei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,6]]},"reference":[{"key":"2_CR1","unstructured":"Antos, A., Szepesv\u00e1ri, C., Munos, R.: Fitted Q-iteration in continuous action-space MDPs. In: NeurIPS (2008)"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Baird, L.: Residual algorithms: reinforcement learning with function approximation. In: Machine Learning Proceedings 1995, pp. 30\u201337. Elsevier (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bonadiman, D., Uva, A., Moschitti, A.: Effective shared representations with multitask learning for community question answering. In: ACL (2017)","DOI":"10.18653\/v1\/E17-2115"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chen, M., Beutel, A., Covington, P., Jain, S., Belletti, F., Chi, E.: Top-k off-policy correction for a reinforce recommender system. In: WSDM (2019)","DOI":"10.1145\/3289600.3290999"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, H.-T., Levent Koc, H., et al.: Wide & deep learning for recommender systems. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 7\u201310. ACM (2016)","DOI":"10.1145\/2988450.2988454"},{"key":"2_CR6","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"2_CR7","unstructured":"de Brebisson, A., Vincent, P.: A cheap linear attention mechanism with fast lookups and fixed-size representations. arXiv preprint arXiv:1609.05866 (2016)"},{"key":"2_CR8","unstructured":"Dulac-Arnold, G., et al.: Deep reinforcement learning in large discrete action spaces. arXiv preprint arXiv:1512.07679 (2015)"},{"key":"2_CR9","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. arXiv preprint arXiv:1812.02900 (2018)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: Continual prediction with LSTM (1999)","DOI":"10.1049\/cp:19991218"},{"key":"2_CR11","unstructured":"Hidasi, B., Karatzoglou, A., et al.: Session-based recommendations with recurrent neural networks. arXiv:1511.06939 (2015)"},{"key":"2_CR12","unstructured":"Kolter, J.Z.: The fixed points of off-policy TD. In: Advances in Neural Information Processing Systems, pp. 2169\u20132177 (2011)"},{"issue":"8","key":"2_CR13","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MC.2009.263","volume":"42","author":"Y Koren","year":"2009","unstructured":"Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30\u201337 (2009)","journal-title":"Computer"},{"key":"2_CR14","unstructured":"Kumar, A., Fu, J., et al.: Stabilizing off-policy Q-learning via bootstrapping error reduction. arXiv:1906.00949 (2019)"},{"key":"2_CR15","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/MIC.2003.1167344","volume":"1","author":"G Linden","year":"2003","unstructured":"Linden, G., Smith, B., York, J.: Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Comput. 1, 76\u201380 (2003)","journal-title":"IEEE Internet Comput."},{"key":"2_CR16","first-page":"560","volume":"3","author":"R Munos","year":"2003","unstructured":"Munos, R.: Error bounds for approximate policy iteration. ICML 3, 560\u2013567 (2003)","journal-title":"ICML"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Peng, H., Li, J., Song, Y., Liu, Y.: Incrementally learning the hierarchical softmax function for neural language models. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.10994"},{"key":"2_CR18","unstructured":"Rong, X.: word2vec parameter learning explained. arXiv:1411.2738 (2014)"},{"key":"2_CR19","unstructured":"Zaeemzadeh, A., Rahnavard, N., Shah, M.: Norm-preservation: why residual networks can become extremely deep? arXiv preprint arXiv:1805.07477 (2018)"},{"issue":"1","key":"2_CR20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3158369","volume":"52","author":"S Zhang","year":"2019","unstructured":"Zhang, S., Yao, L., Sun, A., Tay, Y.: Deep learning based recommender system: a survey and new perspectives. CSUR 52(1), 1\u201338 (2019)","journal-title":"CSUR"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, L., Ding, Z., et al.: Deep reinforcement learning for list-wise recommendations. arXiv:1801.00209 (2017)","DOI":"10.1145\/3240323.3240374"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, L., Ding, Z., et al.: Recommendations with negative feedback via pairwise deep reinforcement learning. In: SIGKDD (2018)","DOI":"10.1145\/3219819.3219886"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Zheng,G., Zhang, F., Zheng, Z., et al.: DRN: a deep reinforcement learning framework for news recommendation. In: WWW (2018)","DOI":"10.1145\/3178876.3185994"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-47426-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T08:34:32Z","timestamp":1666514072000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-47426-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030474256","9783030474263"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-47426-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"6 May 2020","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":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 May 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 May 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2020.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":"CMT System","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"628","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":"135","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":"21% - 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":"3-4","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":"6-8","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}