{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T02:15:23Z","timestamp":1778638523052,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698936","type":"print"},{"value":"9789819698943","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9894-3_3","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T19:56:38Z","timestamp":1753473398000},"page":"27-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Personalized Multi-objective Learning Path Recommendation via Hierarchical Reinforcement Learning and Knowledge Tracing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9580-6802","authenticated-orcid":false,"given":"Yunxuan","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3171-4618","authenticated-orcid":false,"given":"Zhengyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7801-0378","authenticated-orcid":false,"given":"Zetao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1145\/3543507.3583259","volume-title":"Proceedings of the ACM Web Conference 2023","author":"Q Cai","year":"2023","unstructured":"Cai, Q., et al.: Two-stage constrained actor-critic for short video recommendation. In: Proceedings of the ACM Web Conference 2023, pp. 865\u2013875 (2023)"},{"key":"3_CR2","first-page":"532","volume-title":"EDM","author":"HS Chang","year":"2015","unstructured":"Chang, H.S., et al.: Modeling exercise relationships in e-learning: A unified approach. In: EDM, pp. 532\u2013535 (2015)"},{"key":"3_CR3","volume-title":"Adaptive learning path navigation based on knowledge tracing and reinforcement learning. arXiv preprint arXiv:2305.04475","author":"JY Chen","year":"2023","unstructured":"Chen, J.Y., Saeedvand, S., Lai, I.W.: Adaptive learning path navigation based on knowledge tracing and reinforcement learning. arXiv preprint arXiv:2305.04475 (2023)"},{"key":"3_CR4","first-page":"332","volume-title":"International Conference on Knowledge Science, Engineering and Management","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Wu, Z., Tang, Y., Zhou, J.: TGKT-based personalized learning path recommendation with reinforcement learning. In: International Conference on Knowledge Science, Engineering and Management, pp. 332\u2013346. Springer (2023)"},{"issue":"3","key":"3_CR5","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tele.2017.02.004","volume":"35","author":"BCL Christudas","year":"2018","unstructured":"Christudas, B.C.L., Kirubakaran, E., Thangaiah, P.R.J.: An evolutionary approach for personalization of content delivery in e-learning systems based on learner behavior forcing compatibility of learning materials. Telematics Inform. 35(3), 520\u2013533 (2018)","journal-title":"Telematics Inform."},{"key":"3_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111521","volume":"291","author":"Y Dong","year":"2024","unstructured":"Dong, Y., Liu, Y., Dong, Y., Wang, Y., Chen, M.: Multi-knowledge enhanced graph convolution for learning resource recommendation. Knowl. Based Syst. 291, 111521 (2024)","journal-title":"Knowl. Based Syst."},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1007\/s10639-017-9637-7","volume":"23","author":"P Dwivedi","year":"2018","unstructured":"Dwivedi, P., Kant, V., Bharadwaj, K.K.: Learning path recommendation based on modified variable length genetic algorithm. Educ. Inf. Technol. 23, 819\u2013836 (2018)","journal-title":"Educ. Inf. Technol."},{"key":"3_CR8","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605269","volume-title":"Item Response Theory","author":"SE Embretson","year":"2013","unstructured":"Embretson, S.E., Reise, S.P.: Item Response Theory. Psychology Press, New York (2013)"},{"issue":"1","key":"3_CR9","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1109\/TCOMM.2021.3119689","volume":"70","author":"Y Geng","year":"2021","unstructured":"Geng, Y., Liu, E., Wang, R., Liu, Y.: Hierarchical reinforcement learning for relay selection and power optimization in two-hop cooperative relay network. IEEE Trans. Commun. 70(1), 171\u2013184 (2021)","journal-title":"IEEE Trans. Commun."},{"key":"3_CR10","first-page":"1861","volume-title":"International Conference on Machine Learning","author":"T Haarnoja","year":"2018","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maxi- mum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"issue":"4","key":"3_CR11","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.1007\/s11277-020-07199-0","volume":"115","author":"W Intayoad","year":"2020","unstructured":"Intayoad, W., Kamyod, C., Temdee, P.: Reinforcement learning based on contextual bandits for personalized online learning recommendation systems. Wirel. Pers. Commun. 115(4), 2917\u20132932 (2020)","journal-title":"Wirel. Pers. Commun."},{"key":"3_CR12","volume-title":"Leveraging skill-to-skill supervision for knowledge tracing. arXiv preprint arXiv:2306.06841","author":"H Kim","year":"2023","unstructured":"Kim, H., Nam, J., Lee, M., Jegal, Y., Song, K.: Leveraging skill-to-skill supervision for knowledge tracing. arXiv preprint arXiv:2306.06841 (2023)"},{"key":"3_CR13","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. Adv. Neural Inf. Proces. Syst. 12 (1999)"},{"key":"3_CR14","volume-title":"RLTutor: Reinforcement learning based adaptive tutoring system by modeling virtual student with fewer interactions. arXiv preprint arXiv:2108.00268","author":"Y Kubotani","year":"2021","unstructured":"Kubotani, Y., Fukuhara, Y., Morishima, S.: RLTutor: Reinforcement learning based adaptive tutoring system by modeling virtual student with fewer interactions. arXiv preprint arXiv:2108.00268 (2021)"},{"key":"3_CR15","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1145\/3583780.3614897","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","author":"Q Li","year":"2023","unstructured":"Li, Q., et al.: Graph enhanced hierarchical reinforcement learning for goal-oriented learning path recommendation. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pp. 1318\u20131327 (2023)"},{"issue":"24","key":"3_CR16","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12244939","volume":"12","author":"K Liang","year":"2023","unstructured":"Liang, K., Zhang, G., Guo, J., Li, W.: An actor-critic hierarchical reinforcement learning model for course recommendation. Electronics. 12(24), 4939 (2023)","journal-title":"Electronics"},{"issue":"1","key":"3_CR17","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/s10639-022-11178-2","volume":"28","author":"Z Liang","year":"2023","unstructured":"Liang, Z., Mu, L., Chen, J., Xie, Q.: Graph path fusion and reinforcement reasoning for recommendation in MOOCS. Educ. Inf. Technol. 28(1), 525\u2013545 (2023)","journal-title":"Educ. Inf. Technol."},{"key":"3_CR18","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1145\/3292500.3330922","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Q Liu","year":"2019","unstructured":"Liu, Q., et al.: Exploiting cognitive structure for adaptive learning. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 627\u2013635 (2019)"},{"issue":"2","key":"3_CR19","doi-asserted-by":"publisher","first-page":"2705","DOI":"10.1109\/TNNLS.2024.3354061","volume":"36","author":"Y Luo","year":"2024","unstructured":"Luo, Y., et al.: Goal-conditioned hierarchical reinforcement learning with high-level model approximation. IEEE Trans. Neural Netw. Learn. Syst. 36(2), 2705\u20132719 (2024)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3_CR20","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"V Mnih","year":"2013","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"3_CR21","first-page":"267","volume-title":"Intelligent Tutoring Systems 13th International Conference, ITS 2016, Zagreb, Croatia, June 7\u201310, 2016. Proceedings 13","author":"J Papou\u0161ek","year":"2016","unstructured":"Papou\u0161ek, J., Stanislav, V., Pel\u00e1nek, R.: Impact of question difficulty on engagement and learning. In: Intelligent Tutoring Systems 13th International Conference, ITS 2016, Zagreb, Croatia, June 7\u201310, 2016. Proceedings 13, pp. 267\u2013272. Springer (2016)"},{"key":"3_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110117","volume":"260","author":"Y Ren","year":"2023","unstructured":"Ren, Y., Liang, K., Shang, Y., Zhang, Y.: MuLOER-San: 2-layer multi-objective framework for exercise recommendation with self-attention networks. Knowl. Based Syst. 260, 110117 (2023)","journal-title":"Knowl. Based Syst."},{"key":"3_CR23","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"J Schulman","year":"2017","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"3_CR24","first-page":"37","volume-title":"Psychology of Learning and Motivation","author":"J Sweller","year":"2011","unstructured":"Sweller, J.: Cognitive load theory. In: Psychology of Learning and Motivation, vol. 55, pp. 37\u201376. Elsevier (2011)"},{"key":"3_CR25","doi-asserted-by":"publisher","first-page":"11607","DOI":"10.1007\/s00521-023-08686-8","volume":"37","author":"JW Tzeng","year":"2023","unstructured":"Tzeng, J.W., Huang, N.F., Chuang, A.C., Huang, T.W., Chang, H.Y.: Massive open online course recommendation system based on a reinforcement learning algorithm. Neural Comput. Applic. 37, 11607\u201311618 (2023)","journal-title":"Neural Comput. Applic."},{"key":"3_CR26","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.1145\/3580305.3599367","volume-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"H Wang","year":"2023","unstructured":"Wang, H., et al.: GMOCAT: A graph-enhanced multi-objective method for computerized adaptive testing. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 2279\u20132289 (2023)"},{"issue":"5","key":"3_CR27","doi-asserted-by":"publisher","DOI":"10.3390\/info12050198","volume":"12","author":"X Wang","year":"2021","unstructured":"Wang, X., et al.: Exploring clustering-based reinforcement learning for personalized book recommendation in digital library. Information. 12(5), 198 (2021)","journal-title":"Information"},{"key":"3_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106481","volume":"210","author":"Z Wu","year":"2020","unstructured":"Wu, Z., Li, M., Tang, Y., Liang, Q.: Exercise recommendation based on knowledge concept prediction. Knowl.-Based Syst. 210, 106481 (2020)","journal-title":"Knowl.-Based Syst."},{"key":"3_CR29","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-67658-2_18","volume-title":"Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2020, Ghent, Belgium, September 14\u201318, 2020, Proceedings, Part I","author":"Y Yang","year":"2021","unstructured":"Yang, Y., et al.: GIKT: A graph-based interaction model for knowledge tracing. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2020, Ghent, Belgium, September 14\u201318, 2020, Proceedings, Part I, pp. 299\u2013315. Springer (2021)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Zaizi, F.E., Qassimi, S., Rakrak, S.: Multi-objective optimization with recommender systems: A systematic review. Inf. Syst., 102233 (2023)","DOI":"10.1016\/j.is.2023.102233"},{"key":"3_CR31","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1145\/3038912.3052580","volume-title":"Proceedings of the 26th international conference on World Wide Web","author":"J Zhang","year":"2017","unstructured":"Zhang, J., Shi, X., King, I., Yeung, D.Y.: Dynamic key-value memory networks for knowledge tracing. In: Proceedings of the 26th international conference on World Wide Web, pp. 765\u2013774 (2017)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9894-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:36:44Z","timestamp":1774661804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9894-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698936","9789819698943"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9894-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}