{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:47:15Z","timestamp":1787017635068,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62177033"],"award-info":[{"award-number":["62177033"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671872","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T00:55:12Z","timestamp":1724547312000},"page":"1621-1630","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Privileged Knowledge State Distillation for Reinforcement Learning-based Educational Path Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3731-1548","authenticated-orcid":false,"given":"Qingyao","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2544-775X","authenticated-orcid":false,"given":"Wei","family":"Xia","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5048-4619","authenticated-orcid":false,"given":"Li'ang","family":"Yin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6458-1586","authenticated-orcid":false,"given":"Jiarui","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-8271","authenticated-orcid":false,"given":"Yong","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2020. MindSpore. https:\/\/www.mindspore.cn\/"},{"key":"e_1_3_2_2_2_1","volume-title":"Multipolar: Multi-source policy aggregation for transfer reinforcement learning between diverse environmental dynamics. arXiv preprint arXiv:1909.13111","author":"Barekatain Mohammadamin","year":"2019","unstructured":"Mohammadamin Barekatain, Ryo Yonetani, and Masashi Hamaya. 2019. Multipolar: Multi-source policy aggregation for transfer reinforcement learning between diverse environmental dynamics. arXiv preprint arXiv:1909.13111 (2019)."},{"key":"e_1_3_2_2_3_1","first-page":"2277","article-title":"Adaptive learning path recommendation based on graph theory and an improved immune algorithm","volume":"13","author":"Bian Cun-Ling","year":"2019","unstructured":"Cun-Ling Bian, De-LiangWang, Shi-Yu Liu,Wei-Gang Lu, and Jun-Yu Dong. 2019. Adaptive learning path recommendation based on graph theory and an improved immune algorithm. KSII Transactions on Internet and Information Systems (TIIS) 13, 5 (2019), 2277--2298.","journal-title":"KSII Transactions on Internet and Information Systems (TIIS)"},{"key":"e_1_3_2_2_4_1","unstructured":"Haw-Shiuan Chang Hwai-Jung Hsu and Kuan-Ta Chen. 2015. Modeling Exercise Relationships in E-Learning: A Unified Approach.. In EDM. 532--535."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8535.2008.00892.x"},{"key":"e_1_3_2_2_6_1","volume-title":"DAS3H: modeling student learning and forgetting for optimally scheduling distributed practice of skills. arXiv preprint arXiv:1905.06873","author":"Choffin Benoit","year":"2019","unstructured":"Benoit Choffin, Fabrice Popineau, Yolaine Bourda, and Jill-Jenn Vie. 2019. DAS3H: modeling student learning and forgetting for optimally scheduling distributed practice of skills. arXiv preprint arXiv:1905.06873 (2019)."},{"key":"e_1_3_2_2_7_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_2_8_1","volume-title":"NIPS 2014 Workshop on Deep Learning","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. In NIPS 2014 Workshop on Deep Learning, December 2014."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"e_1_3_2_2_10_1","volume-title":"Learning path recommendation based on modified variable length genetic algorithm. Education and information technologies 23, 2","author":"Dwivedi Pragya","year":"2018","unstructured":"Pragya Dwivedi, Vibhor Kant, and Kamal K Bharadwaj. 2018. Learning path recommendation based on modified variable length genetic algorithm. Education and information technologies 23, 2 (2018), 819--836."},{"key":"e_1_3_2_2_11_1","volume-title":"Constructing a personalized learning path using genetic algorithms approach. arXiv preprint arXiv:2104.11276","author":"Elshani Lumbardh","year":"2021","unstructured":"Lumbardh Elshani and Krenare Pireva Nu\u00e7i. 2021. Constructing a personalized learning path using genetic algorithms approach. arXiv preprint arXiv:2104.11276 (2021)."},{"key":"e_1_3_2_2_12_1","volume-title":"International conference on machine learning. PMLR, 1587--1596","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. In International conference on machine learning. PMLR, 1587--1596."},{"key":"e_1_3_2_2_13_1","unstructured":"Jibing Gong Yao Wan Ye Liu Xuewen Li Yi Zhao Cheng Wang Yuting Lin Xiaohan Fang Wenzheng Feng Jingyi Zhang et al. 2022. Reinforced moocs concept recommendation in heterogeneous information networks. ACM Transactions on the Web (2022)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401057"},{"key":"e_1_3_2_2_15_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861-- 1870."},{"key":"e_1_3_2_2_16_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-020-07199-0"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622737.1622748"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_20_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_21_1","volume-title":"Actor-critic algorithms. Advances in neural information processing systems 12","author":"Konda Vijay","year":"1999","unstructured":"Vijay Konda and John Tsitsiklis. 1999. Actor-critic algorithms. Advances in neural information processing systems 12 (1999)."},{"key":"e_1_3_2_2_22_1","volume-title":"RLTutor: Reinforcement Learning Based Adaptive Tutoring System by Modeling Virtual Student with Fewer Interactions. arXiv preprint arXiv:2108.00268","author":"Kubotani Yoshiki","year":"2021","unstructured":"Yoshiki Kubotani, Yoshihiro Fukuhara, and Shigeo Morishima. 2021. RLTutor: Reinforcement Learning Based Adaptive Tutoring System by Modeling Virtual Student with Fewer Interactions. arXiv preprint arXiv:2108.00268 (2021)."},{"key":"e_1_3_2_2_23_1","volume-title":"Rma: Rapid motor adaptation for legged robots. arXiv preprint arXiv:2107.04034","author":"Kumar Ashish","year":"2021","unstructured":"Ashish Kumar, Zipeng Fu, Deepak Pathak, and Jitendra Malik. 2021. Rma: Rapid motor adaptation for legged robots. arXiv preprint arXiv:2107.04034 (2021)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614897"},{"key":"e_1_3_2_2_25_1","volume-title":"A survey on reinforcement learning for recommender systems. arXiv preprint arXiv:2109.10665","author":"Lin Yuanguo","year":"2021","unstructured":"Yuanguo Lin, Yong Liu, Fan Lin, Lixin Zou, PengchengWu,Wenhua Zeng, Huanhuan Chen, and Chunyan Miao. 2021. A survey on reinforcement learning for recommender systems. arXiv preprint arXiv:2109.10665 (2021)."},{"key":"e_1_3_2_2_26_1","volume-title":"KDCRec: Knowledge Distillation for Counterfactual Recommendation Via Uniform Data","author":"Liu Dugang","year":"2022","unstructured":"Dugang Liu, Pengxiang Cheng, Zinan Lin, Jinwei Luo, Zhenhua Dong, Xiuqiang He,Weike Pan, and Zhong Ming. 2022. KDCRec: Knowledge Distillation for Counterfactual Recommendation Via Uniform Data. IEEE Transactions on Knowledge and Data Engineering (2022)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330922"},{"key":"e_1_3_2_2_28_1","volume-title":"Unifying distillation and privileged information. arXiv preprint arXiv:1511.03643","author":"Lopez-Paz David","year":"2015","unstructured":"David Lopez-Paz, L\u00e9on Bottou, Bernhard Sch\u00f6lkopf, and Vladimir Vapnik. 2015. Unifying distillation and privileged information. arXiv preprint arXiv:1511.03643 (2015)."},{"key":"e_1_3_2_2_29_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113596"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3350546.3352513"},{"key":"e_1_3_2_2_32_1","volume-title":"Deep knowledge tracing. Advances in neural information processing systems 28","author":"Piech Chris","year":"2015","unstructured":"Chris Piech, Jonathan Bassen, Jonathan Huang, Surya Ganguli, Mehran Sahami, Leonidas J Guibas, and Jascha Sohl-Dickstein. 2015. Deep knowledge tracing. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_2_33_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_34_1","volume-title":"Understanding LSTM--a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586","author":"Staudemeyer Ralf C","year":"2019","unstructured":"Ralf C Staudemeyer and Eric Rothstein Morris. 2019. Understanding LSTM--a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586 (2019)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462929"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106481"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498476"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403309"},{"key":"e_1_3_2_2_39_1","first-page":"34954","article-title":"Perfectdou: Dominating doudizhu with perfect information distillation","volume":"35","author":"Yang Guan","year":"2022","unstructured":"Guan Yang, Minghuan Liu, Weijun Hong, Weinan Zhang, Fei Fang, Guangjun Zeng, and Yue Lin. 2022. Perfectdou: Dominating doudizhu with perfect information distillation. Advances in Neural Information Processing Systems 35 (2022), 34954--34965.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_40_1","volume-title":"Automatic Learning Path Recommendation for Open Source Projects Using Deep Learning on Knowledge Graphs. In 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC)","author":"Yin Hang","unstructured":"Hang Yin, Zhiyu Sun, Yanchun Sun, and Gang Huang. 2021. Automatic Learning Path Recommendation for Open Source Projects Using Deep Learning on Knowledge Graphs. In 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC). IEEE, 824--833."},{"key":"e_1_3_2_2_41_1","first-page":"76","article-title":"Recommender Systems in E-learning","volume":"1","author":"Zhang Qian","year":"2021","unstructured":"Qian Zhang, Jie Lu, and Guangquan Zhang. 2021. Recommender Systems in E-learning. Journal of Smart Environments and Green Computing 1, 2 (2021), 76--89.","journal-title":"Journal of Smart Environments and Green Computing"},{"key":"e_1_3_2_2_42_1","volume-title":"Personalized learning full-path recommendation model based on LSTM neural networks. Information sciences 444","author":"Zhou Yuwen","year":"2018","unstructured":"Yuwen Zhou, Changqin Huang, Qintai Hu, Jia Zhu, and Yong Tang. 2018. Personalized learning full-path recommendation model based on LSTM neural networks. Information sciences 444 (2018), 135--152."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671872","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:04:15Z","timestamp":1750277055000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671872"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":42,"alternative-id":["10.1145\/3637528.3671872","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671872","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}