{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:28:49Z","timestamp":1777501729552,"version":"3.51.4"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031683084","type":"print"},{"value":"9783031683091","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-68309-1_22","type":"book-chapter","created":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T14:02:25Z","timestamp":1723903345000},"page":"258-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Soft Actor-Critic Algorithm for\u00a0Sequential Recommendation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7477-9287","authenticated-orcid":false,"given":"Hyejin","family":"Hong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2441-9714","authenticated-orcid":false,"given":"Yusuke","family":"Kimura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7079-8247","authenticated-orcid":false,"given":"Kenji","family":"Hatano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,18]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Afsar, M.M., Crump, T., Far, B.: Reinforcement learning based recommender systems: a survey. ACM Comput. Surv. 55(7) (2022)","DOI":"10.1145\/3543846"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bangari, S., et\u00a0al.: A review on reinforcement learning based news recommendation systems and its challenges. In: Proceedings of 2021 International Conference on Artificial Intelligence and Smart Systems, pp. 260\u2013265 (2021)","DOI":"10.1109\/ICAIS50930.2021.9395812"},{"key":"22_CR3","unstructured":"Barakat, A., Bianchi, P., Lehmann, J.: Analysis of a target-based actor-critic algorithm with linear function approximation. In: Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, pp. 991\u20131040. PMLR (2022)"},{"key":"22_CR4","unstructured":"Fujimoto, S., et\u00a0al.: Addressing function approximation error in actor-critic methods. In: Proceedings of the 35th International Conference on Machine Learning, vol.\u00a080 (2018)"},{"key":"22_CR5","unstructured":"Haarnoja, T., et\u00a0al.: soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th International Conference on Machine Learning, vol.\u00a080 (2018)"},{"key":"22_CR6","unstructured":"Kumar, A., Daum\u00e9, H.: Learning task grouping and overlap in multi-task learning. In: Proceedings of the 29th International Conference on International Conference on Machine Learning, pp. 1723\u20131730. Omnipress (2012)"},{"key":"22_CR7","unstructured":"Lin, X., et\u00a0al.: Pareto multi-task learning. In: Thirty-third Conference on Neural Information Processing Systems (NeurIPS), pp. 12037\u201312047 (2019)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Lin, Y., et\u00a0al.: A survey on reinforcement learning for recommender systems. IEEE Trans. Neural Netw. Learn. Syst. 1\u201321 (2023)","DOI":"10.1109\/TNNLS.2023.3280161"},{"key":"22_CR9","unstructured":"Liu, Z., Wen, S., Quan, Y.: Deep reinforcement learning based group recommender system. arXiv preprint arXiv:2106.06900 (2021)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Multi-task recommendations with reinforcement learning. In: Proceedings of the ACM Web Conference 2023, pp. 1273\u20131282 (2023)","DOI":"10.1145\/3543507.3583467"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Ma, J., et\u00a0al.: Off-policy learning in two-stage recommender systems. In: Proceedings of The Web Conference 2020, pp. 463\u2013473. ACM (2020)","DOI":"10.1145\/3366423.3380130"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Ma, X., et\u00a0al.: Entire space multi-task model: an effective approach for estimating post-click conversion rate. In: Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 1137\u20131140 (2018)","DOI":"10.1145\/3209978.3210104"},{"key":"22_CR13","unstructured":"Shani, G., Meisles, A., Gleyzer, Y., Rokach, L., Ben-Shimon, D.: a stereotypes-based hybrid recommender system for media items. In: Proceedings of AAAI Workshop on Intelligent Techniques for Web Personalization, pp. 76\u201383 (2007)"},{"key":"22_CR14","unstructured":"Sohail, S.S., Siddiqui, J., Ali, R.: Classifications of recommender systems: a review. J. Eng. Sci. Technol. Rev. 10(4) (2017)"},{"issue":"3","key":"22_CR15","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s11257-018-9205-x","volume":"28","author":"W Wu","year":"2018","unstructured":"Wu, W., Chen, L., Zhao, Y.: Personalizing recommendation diversity based on user personality. User Model. User-Adap. Inter. 28(3), 237\u2013276 (2018)","journal-title":"User Model. User-Adap. Inter."},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Xin, X., et\u00a0al.: Self-supervised reinforcement learning for recommender systems. In: Proceedings of the 43rd International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 931\u2013940 (2020)","DOI":"10.1145\/3397271.3401147"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yao, L., Sun, A., Tay, Y.: Deep learning based recommender system: a survey and new perspectives. ACM Comput. Surv. 52(1) (2019)","DOI":"10.1145\/3285029"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, L.Y., et\u00a0al.: An overestimation reduction method based on the multi-step weighted double estimation using value-decomposition multi-agent reinforcement learning. Neural Process. Lett. 56(3), 1\u201321 (2024)","DOI":"10.1007\/s11063-024-11611-2"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-68309-1_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T14:04:57Z","timestamp":1723903497000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-68309-1_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031683084","9783031683091"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-68309-1_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"18 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEXA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database and Expert Systems Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dexa2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dexa.org\/dexa2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}