{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:13:57Z","timestamp":1776122037223,"version":"3.50.1"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031984198","type":"print"},{"value":"9783031984204","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\/978-3-031-98420-4_28","type":"book-chapter","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T20:13:38Z","timestamp":1752783218000},"page":"393-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Generalized Apprenticeship Learning Framework for\u00a0Capturing Evolving Student Pedagogical Strategies"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5086-7399","authenticated-orcid":false,"given":"Md Mirajul","family":"Islam","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0026-9096","authenticated-orcid":false,"given":"Xi","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5460-9773","authenticated-orcid":false,"given":"Rajesh","family":"Debnath","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6344-9663","authenticated-orcid":false,"given":"Adittya","family":"Shoukarjya Saha","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1765-7837","authenticated-orcid":false,"given":"Min","family":"Chi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the 21st International Conference on Machine Learning, p.\u00a01. ACM (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"28_CR2","unstructured":"Abdelshiheed, M., Hostetter, J.W., Barnes, T., Chi, M.: Bridging declarative, procedural, and conditional metacognitive knowledge gap using deep reinforcement learning. In: Proceedings of the Annual Meeting of the Cognitive Science Society. No.\u00a045 in CogSci \u201923\u2019 (2023)"},{"key":"28_CR3","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Man\u00e9, D.: Concrete problems in ai safety. arXiv preprint arXiv:1606.06565 (2016)"},{"key":"28_CR4","unstructured":"Asoh, H., Akaho, M.S.S., Kamishima, T., Hasida, K., Aramaki, E., Kohro, T.: An application of inverse reinforcement learning to medical records of diabetes treatment. In: ECMLPKDD2013 Workshop on Reinforcement Learning with Generalized Feedback (2013)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Ausin, M.S., Maniktala, M., Barnes, T., Chi, M.: Exploring the impact of simple explanations and agency on batch deep reinforcement learning induced pedagogical policies. In: AIED, pp. 472\u2013485 (2020)","DOI":"10.1007\/978-3-030-52237-7_38"},{"key":"28_CR6","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.engappai.2018.06.007","volume":"74","author":"H Azizsoltani","year":"2018","unstructured":"Azizsoltani, H., Sadeghi, E.: Adaptive sequential strategy for risk estimation of engineering systems using gaussian process regression active learning. Eng. Appl. Artif. Intell. 74, 146\u2013165 (2018)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"28_CR7","unstructured":"Babes, M., Marivate, V., Subramanian, K., Littman, M.L.: Apprenticeship learning about multiple intentions. In: Proceedings of the 28th ICML, pp. 897\u2013904 (2011)"},{"key":"28_CR8","unstructured":"Chan, A.J., van\u00a0der Schaar, M.: Scalable bayesian inverse reinforcement learning. arXiv preprint arXiv:2102.06483 (2021)"},{"key":"28_CR9","unstructured":"Choi, J., Kim, K.E.: Nonparametric bayesian inverse reinforcement learning for multiple reward functions. In: Advances in Neural Information Processing Systems, pp. 305\u2013313 (2012)"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Dimitrakakis, C., Rothkopf, C.A.: Bayesian multitask inverse reinforcement learning. In: European Workshop on Reinforcement Learning, pp. 273\u2013284. Springer (2011)","DOI":"10.1007\/978-3-642-29946-9_27"},{"key":"28_CR11","unstructured":"Fan, J., Wang, Z., Xie, Y., Yang, Z.: A theoretical analysis of deep q-learning. In: Learning for Dynamics and Control, pp. 486\u2013489. PMLR (2020)"},{"key":"28_CR12","unstructured":"Finn, C., Levine, S., Abbeel, P.: Guided cost learning: Deep inverse optimal control via policy optimization. In: International Conference on Machine Learning, pp. 49\u201358. PMLR (2016)"},{"key":"28_CR13","unstructured":"Finn, C., Yu, T., Zhang, T., Abbeel, P., Levine, S.: One-shot visual imitation learning via meta-learning. In: Conference on Robot Learning, pp. 357\u2013368. PMLR (2017)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Friedman, J., Hastie, T., Tibshirani, R.: The elements of statistical learning, vol.\u00a01. Springer series in statistics New York (2001)","DOI":"10.1007\/978-0-387-21606-5_1"},{"key":"28_CR15","unstructured":"Gleave, A., et al.: imitation: clean imitation learning implementations (2022)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Goyal, P., Niekum, S., Mooney, R.J.: Using natural language for reward shaping in reinforcement learning. arXiv preprint arXiv:1903.02020 (2019)","DOI":"10.24963\/ijcai.2019\/331"},{"issue":"4","key":"28_CR17","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1109\/TIT.2005.844072","volume":"51","author":"D Guo","year":"2005","unstructured":"Guo, D., Shamai, S., Verd\u00fa, S.: Mutual information and minimum mean-square error in gaussian channels. IEEE Trans. Inf. Theory 51(4), 1261\u20131282 (2005)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Hallac, D., Vare, S., Boyd, S., Leskovec, J.: Toeplitz inverse covariance-based clustering of multivariate time series data. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 215\u2013223 (2017)","DOI":"10.1145\/3097983.3098060"},{"key":"28_CR19","unstructured":"Hausman, K., Chebotar, Y., Schaal, S., Sukhatme, G., Lim, J.J.: Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets. Advances in neural information processing systems 30 (2017)"},{"key":"28_CR20","unstructured":"Hinton, G., Roweis, S.: Stochastic neighbor embedding. In: Proceedings of the 16th International Conference on Neural Information Processing Systems, pp. 857\u2013864. NIPS\u201902, MIT Press, Cambridge, MA, USA (2002)"},{"key":"28_CR21","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. Advances in neural information processing systems 29 (2016)"},{"key":"28_CR22","unstructured":"Islam, M.M., Yang, X., Hostetter, J., Saha, A.S., Chi, M.: A generalized apprenticeship learning framework for modeling heterogeneous student pedagogical strategies. In: Proceedings of the 17th International Conference on Educational Data Mining, pp. 131\u2013142. International Educational Data Mining Society (2024)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Jain, V., Doshi, P., Banerjee, B.: Model-free irl using maximum likelihood estimation. In: Proceedings of the AAAI, vol.\u00a033, pp. 3951\u20133958 (2019)","DOI":"10.1609\/aaai.v33i01.33013951"},{"key":"28_CR24","first-page":"7354","volume":"33","author":"D Jarrett","year":"2020","unstructured":"Jarrett, D., Bica, I., van der Schaar, M.: Strictly batch imitation learning by energy-based distribution matching. Adv. Neural. Inf. Process. Syst. 33, 7354\u20137365 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Ju, S., Zhou, G., Abdelshiheed, M., Barnes, T., Chi:, M.: Evaluating critical reinforcement learning framework in the field. AIED, pp. 215\u2013227 (2021)","DOI":"10.1007\/978-3-030-78292-4_18"},{"key":"28_CR26","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Klein, E., Geist, M., Pietquin, O.: Batch, off-policy and model-free apprenticeship learning. In: European Workshop on Reinforcement Learning, pp. 285\u2013296. Springer (2011)","DOI":"10.1007\/978-3-642-29946-9_28"},{"key":"28_CR28","unstructured":"Kostrikov, I., Agrawal, K.K., Dwibedi, D., Levine, S., Tompson, J.: Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning. International Conference on Learning Representations (2018)"},{"key":"28_CR29","unstructured":"Kostrikov, I., Nachum, O., Tompson, J.: Imitation learning via off-policy distribution matching. In: International Conference on Learning Representations (2020)"},{"key":"28_CR30","unstructured":"Krishnan, S., Garg, A., Liaw, R., Miller, L., Pokorny, F.T., Goldberg, K.: Hirl: hierarchical inverse reinforcement learning for long-horizon tasks with delayed rewards. arXiv preprint arXiv:1604.06508 (2016)"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Lee, D., Srinivasan, S., Doshi-Velez, F.: Truly batch apprenticeship learning with deep successor features. arXiv preprint arXiv:1903.10077 (2019)","DOI":"10.24963\/ijcai.2019\/819"},{"key":"28_CR32","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":"28_CR33","unstructured":"Mandel, T., et\u00a0al.: Offline policy evaluation across representations with applications to educational games. In: AAMAS, pp. 1077\u20131084 (2014)"},{"key":"28_CR34","unstructured":"Mao, Y., Lin, C., Chi, M.: Deep learning vs. bayesian knowledge tracing: Student models for interventions. J. Educ. Data Mining (2018)"},{"key":"28_CR35","unstructured":"Mao, Y., Marwan, S., Price, T.W., Barnes, T., Chi, M.: What time is it? student modeling needs to know. In: Proceedings of The 13th International Conference on Educational Data Mining (EDM 2020), pp. 171\u2013182 (2020)"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Pan, M., Li, Y., Zhou, X., Liu, Z., Song, R., Lu, H., Luo, J.: Dissecting the learning curve of taxi drivers: A data-driven approach. In: Proceedings of the 2019 SIAM International Conference on Data Mining, pp. 783\u2013791 (2019)","DOI":"10.1137\/1.9781611975673.88"},{"issue":"1","key":"28_CR37","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1162\/neco.1991.3.1.88","volume":"3","author":"DA Pomerleau","year":"1991","unstructured":"Pomerleau, D.A.: Efficient training of artificial neural networks for autonomous navigation. Neural Comput. 3(1), 88\u201397 (1991)","journal-title":"Neural Comput."},{"key":"28_CR38","first-page":"472","volume":"16","author":"AN Rafferty","year":"2016","unstructured":"Rafferty, A.N., Jansen, R., Griffiths, T.L.: Using inverse planning for personalized feedback. EDM 16, 472\u2013477 (2016)","journal-title":"EDM"},{"issue":"3","key":"28_CR39","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1111\/cogs.12157","volume":"39","author":"AN Rafferty","year":"2015","unstructured":"Rafferty, A.N., LaMar, M.M., Griffiths, T.L.: Inferring learners\u2019 knowledge from their actions. Cogn. Sci. 39(3), 584\u2013618 (2015)","journal-title":"Cogn. Sci."},{"key":"28_CR40","unstructured":"Raghu, A., Komorowski, M., Celi, L.A., Szolovits, P., Ghassemi, M.: Continuous state-space models for optimal sepsis treatment: a deep reinforcement learning approach. In: Machine Learning for Healthcare Conference, pp. 147\u2013163 (2017)"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Raza, S., Haider, S., Williams, M.A.: Teaching coordinated strategies to soccer robots via imitation. In: IEEE International Conference on Robotics and Biomimetics, pp. 1434\u20131439 (2012)","DOI":"10.1109\/ROBIO.2012.6491170"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Rowe, J.P., Lester, J.C.: Improving student problem solving in narrative-centered learning environments: a modular reinforcement learning framework. In: AIED, pp. 419\u2013428. Springer (2015)","DOI":"10.1007\/978-3-319-19773-9_42"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Shen, S., Chi, M.: Reinforcement learning: the sooner the better, or the later the better? In: UMAP, pp. 37\u201344. ACM (2016)","DOI":"10.1145\/2930238.2930247"},{"key":"28_CR44","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT press (2018)"},{"key":"28_CR45","unstructured":"Syed, U., Schapire, R.E.: Imitation learning with a value-based prior. arXiv preprint arXiv:1206.5290 (2012)"},{"key":"28_CR46","unstructured":"Wang, J., Roberts, D., Enquobahrie, A.: Inferring continuous treatment doses from historical data via model-based entropy-regularized reinforcement learning. In: Asian Conference on Machine Learning, pp. 433\u2013448. PMLR (2020)"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Wang, L., Tang, R., He, X., He, X.: Hierarchical imitation learning via subgoal representation learning for dynamic treatment recommendation. In: Proceedings of the Fifteenth ACM International Conference on WSDM (2022)","DOI":"10.1145\/3488560.3498535"},{"key":"28_CR48","unstructured":"Wang, L., Yu, W., Cheng, W., Zong, B., Chen, H.: Hierarchical imitation learning with contextual bandits for dynamic treatment regimes. In: RL4RealLife Workshop in the 38 th ICML (2021)"},{"key":"28_CR49","doi-asserted-by":"crossref","unstructured":"Wang, P., Rowe, J., Min, W., Mott, B., Lester, J.: Interactive narrative personalization with deep reinforcement learning. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/538"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Yang, X., Gao, G., Chi, M.: Hierarchical apprenticeship learning for disease progression modeling. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI \u201923 (2023)","DOI":"10.24963\/ijcai.2023\/265"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, Y., Chi, M.: Multi-series time-aware sequence partitioning for disease progression modeling. In: Proceedings of the 30th International Joint Conference on Artificial Intelligence (2021)","DOI":"10.24963\/ijcai.2021\/493"},{"key":"28_CR52","unstructured":"Yang, X., Zhou, G., Taub, M., Azevedo, R., Chi, M.: Student subtyping via em-inverse reinforcement learning. International Educational Data Mining Society (2020)"},{"key":"28_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, G., Azizsoltani, H., Ausin, M.S., Barnes, T., Chi, M.: Hierarchical reinforcement learning for pedagogical policy induction. In: AIED, pp. 544\u2013556 (2019)","DOI":"10.1007\/978-3-030-23204-7_45"},{"key":"28_CR54","unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., Dey, A.K., et\u00a0al.: Maximum entropy inverse reinforcement learning. In: AAAI, vol.\u00a08, pp. 1433\u20131438. Chicago, IL, USA (2008)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-98420-4_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T13:42:39Z","timestamp":1757252559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-98420-4_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031984198","9783031984204"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-98420-4_28","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":"15 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Palermo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2025.itd.cnr.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}