{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:26:32Z","timestamp":1780586792838,"version":"3.54.1"},"reference-count":72,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":1421,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000081","name":"Directorate for Education and Human Resources","doi-asserted-by":"publisher","award":["1726550"],"award-info":[{"award-number":["1726550"]}],"id":[{"id":"10.13039\/100000081","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Artificial Intelligence in Education"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s40593-021-00269-9","type":"journal-article","created":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T14:02:57Z","timestamp":1629122577000},"page":"454-500","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":8,"title":["Leveraging Granularity: Hierarchical Reinforcement Learning for Pedagogical Policy Induction"],"prefix":"10.1016","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-4854","authenticated-orcid":false,"given":"Guojing","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamoon","family":"Azizsoltani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markel Sanz","family":"Ausin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiffany","family":"Barnes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1007\/s40593-021-00269-9_bib1","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1037\/0003-066X.48.1.35","article-title":"Problem solving and learning","volume":"48","author":"Anderson","year":"1993","journal-title":"American Psychologist"},{"issue":"2","key":"10.1007\/s40593-021-00269-9_bib2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1207\/s15327809jls0402_2","article-title":"Cognitive tutors: Lessons learned","volume":"4","author":"Anderson","year":"1995","journal-title":"The journal of the learning sciences"},{"key":"10.1007\/s40593-021-00269-9_bib3","unstructured":"Andrychowicz, M., Baker, B., & et al. (2018). Learning dexterous in-hand manipulation. arXiv:1808.00177."},{"key":"10.1007\/s40593-021-00269-9_bib4","doi-asserted-by":"crossref","unstructured":"Azizsoltani, H., Kim, Y. J., Ausin, M. S., Barnes, T., & Chi, M. (2019). Unobserved is not equal to non-existent: Using gaussian processes to infer immediate rewards across contexts. IJCAI, 1974\u20131980.","DOI":"10.24963\/ijcai.2019\/273"},{"key":"10.1007\/s40593-021-00269-9_bib5","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.engappai.2018.06.007","article-title":"Adaptive sequential strategy for risk estimation of engineering systems using gaussian process regression active learning","volume":"74","author":"Azizsoltani","year":"2018","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"1-2","key":"10.1007\/s40593-021-00269-9_bib6","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","article-title":"Recent advances in hierarchical reinforcement learning","volume":"13","author":"Barto","year":"2003","journal-title":"Discrete event dynamic systems"},{"issue":"552-557","key":"10.1007\/s40593-021-00269-9_bib7","first-page":"1","article-title":"Advisor: a machine learning architecture for intelligent tutor construction","volume":"2000","author":"Beck","year":"2000","journal-title":"AAAI\/IAAI"},{"key":"10.1007\/s40593-021-00269-9_bib8","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1017\/CBO9780511840975.004","article-title":"The zone of proximal development in vygotsky\u2019s analysis of learning and instruction","volume":"1","author":"Chaiklin","year":"2003","journal-title":"Vygotsky\u2019s educational theory in cultural context"},{"key":"10.1007\/s40593-021-00269-9_bib9","first-page":"409","article-title":"Accelerated future learning via explicit instruction of a problem solving strategy","volume":"158","author":"Chi","year":"2007","journal-title":"Frontiers In Artificial Intelligence And Applications"},{"issue":"1","key":"10.1007\/s40593-021-00269-9_bib10","first-page":"25","article-title":"Meta-cognitive strategy instruction in intelligent tutoring systems: how, when, and why","volume":"13","author":"Chi","year":"2010","journal-title":"Educational Technology & Society"},{"issue":"1-2","key":"10.1007\/s40593-021-00269-9_bib11","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11257-010-9093-1","article-title":"Empirically evaluating the application of reinforcement learning to the induction of effective and adaptive pedagogical strategies","volume":"21","author":"Chi","year":"2011","journal-title":"User Modeling and User-Adapted Interaction"},{"key":"10.1007\/s40593-021-00269-9_bib12","unstructured":"Clement, B., Oudeyer, P. Y., & Lopes, M. (2016). A comparison of automatic teaching strategies for heterogeneous student populations. In EDM 16-9th international conference on educational data mining."},{"key":"10.1007\/s40593-021-00269-9_bib13","unstructured":"Cronbach, L. J., & Snow, R. E. (1977). Aptitudes and instructional methods: A handbook for research on interactions. Irvington."},{"key":"10.1007\/s40593-021-00269-9_bib14","doi-asserted-by":"crossref","unstructured":"Cuay\u00e1huitl, H., Dethlefs, N., Frommberger, L., Richter, K. F., & Bateman, J. (2010). Generating adaptive route instructions using hierarchical reinforcement learning. In International conference on spatial cognition (pp. 319\u2013334). Springer.","DOI":"10.1007\/978-3-642-14749-4_27"},{"key":"10.1007\/s40593-021-00269-9_bib15","doi-asserted-by":"crossref","unstructured":"Doroudi, S., Aleven, V., & Brunskill, E. (2017). Robust evaluation matrix: Towards a more principled offline exploration of instructional policies. In Proceedings of the fourth (2017) ACM conference on learning@ scale (pp. 3\u201312).","DOI":"10.1145\/3051457.3051463"},{"issue":"4","key":"10.1007\/s40593-021-00269-9_bib16","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1007\/s40593-019-00187-x","article-title":"Where\u2019s the reward?","volume":"29","author":"Doroudi","year":"2019","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"10.1007\/s40593-021-00269-9_bib17","first-page":"116","article-title":"Multivariate statistics: a vector space approach","volume":"512","author":"Eaton","year":"1983","journal-title":"John Wiley & Sons, Inc., 605 Third Ave., New York, NY 10158, USA, 1983"},{"key":"10.1007\/s40593-021-00269-9_bib18","series-title":"An introduction to probability theory and its applications, Vol. 2","author":"Feller","year":"2008"},{"key":"10.1007\/s40593-021-00269-9_bib19","unstructured":"Goldberg, P. W., Williams, C. K., & et al. (1998). Regression with input-dependent noise: a gaussian process treatment. In NIPS (pp. 493\u2013499)."},{"issue":"4","key":"10.1007\/s40593-021-00269-9_bib20","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1109\/TIT.2005.844072","article-title":"Mutual information and minimum mean-square error in gaussian channels","volume":"51","author":"Guo","year":"2005","journal-title":"IEEE Transactions on Information Theory"},{"key":"10.1007\/s40593-021-00269-9_bib21","unstructured":"Haarnoja, T., Zhou, A., & et al. (2018). Soft actor-critic algorithms and applications. arXiv:1812.05905."},{"issue":"1","key":"10.1007\/s40593-021-00269-9_bib22","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s10489-008-0115-1","article-title":"Learning teaching strategies in an adaptive and intelligent educational system through reinforcement learning","volume":"31","author":"Iglesias","year":"2009","journal-title":"Applied Intelligence"},{"issue":"4","key":"10.1007\/s40593-021-00269-9_bib23","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.knosys.2009.01.007","article-title":"Reinforcement learning of pedagogical policies in adaptive and intelligent educational systems","volume":"22","author":"Iglesias","year":"2009","journal-title":"Knowledge-Based Systems"},{"issue":"3","key":"10.1007\/s40593-021-00269-9_bib24","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s11251-009-9102-0","article-title":"Expertise reversal effect and its instructional implications: Introduction to the special issue","volume":"38","author":"Kalyuga","year":"2010","journal-title":"Instructional Science"},{"key":"10.1007\/s40593-021-00269-9_bib25","unstructured":"Kulkarni, T. D., Narasimhan, K., Saeedi, A., & Tenenbaum, J. (2016). Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. In Advances in neural information processing systems (pp. 3675\u20133683)."},{"key":"10.1007\/s40593-021-00269-9_bib26","unstructured":"Lillicrap, T. P., Hunt, J. J., & et al. (2015). Continuous control with deep reinforcement learning. arXiv:1509.02971."},{"key":"10.1007\/s40593-021-00269-9_bib27","unstructured":"Liz, B., Dreyfus, T., Mason, J., Tsamir, P., Watson, A., & Zaslavsky, O. (2006). Exemplification in mathematics education. In Proceedings of the 30th conference of the international group for the psychology of mathematics education. ERIC, (Vol. 1 pp. 126\u2013154)."},{"key":"10.1007\/s40593-021-00269-9_bib28","doi-asserted-by":"crossref","unstructured":"Mandel, T., Liu, Y. E., Levine, S., Brunskill, E., & Popovic, Z. (2014). Offline policy evaluation across representations with applications to educational games. In Proceedings of the 2014 international conference on autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems (pp. 1077\u20131084).","DOI":"10.65109\/TNVS8310"},{"key":"10.1007\/s40593-021-00269-9_bib29","doi-asserted-by":"crossref","unstructured":"McLaren, B. M., van Gog, T., Ganoe, C., Yaron, D., & Karabinos, M. (2014). Exploring the assistance dilemma: Comparing instructional support in examples and problems. In Intelligent tutoring systems (pp. 354\u2013361). Springer.","DOI":"10.1007\/978-3-319-07221-0_44"},{"key":"10.1007\/s40593-021-00269-9_bib30","doi-asserted-by":"crossref","unstructured":"McLaren, B. M., & Isotani, S. (2011). When is it best to learn with all worked examples?. In International conference on artificial intelligence in education (pp. 222\u2013229). Springer.","DOI":"10.1007\/978-3-642-21869-9_30"},{"key":"10.1007\/s40593-021-00269-9_bib31","unstructured":"McLaren, B. M., Lim, S. J., & Koedinger, K. R. (2008). When and how often should worked examples be given to students? new results and a summary of the current state of research. In Cogsci (pp. 2176\u20132181)."},{"issue":"7540","key":"10.1007\/s40593-021-00269-9_bib32","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1007\/s40593-021-00269-9_bib33","doi-asserted-by":"crossref","unstructured":"Najar, A. S., Mitrovic, A., & McLaren, B. M. (2014). Adaptive support versus alternating worked examples and tutored problems: Which leads to better learning?. In UMAP (pp. 171\u2013182). Springer.","DOI":"10.1007\/978-3-319-08786-3_15"},{"issue":"4","key":"10.1007\/s40593-021-00269-9_bib34","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/3072959.3073602","article-title":"Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"Peng","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"2","key":"10.1007\/s40593-021-00269-9_bib35","doi-asserted-by":"crossref","first-page":"4064","DOI":"10.1016\/j.sbspro.2010.03.641","article-title":"Adaptive intelligent tutoring systems for e-learning systems","volume":"2","author":"Phobun","year":"2010","journal-title":"Procedia-Social and Behavioral Sciences"},{"issue":"6","key":"10.1007\/s40593-021-00269-9_bib36","doi-asserted-by":"crossref","first-page":"1290","DOI":"10.1111\/cogs.12290","article-title":"Faster teaching via pomdp planning","volume":"40","author":"Rafferty","year":"2016","journal-title":"Cognitive science"},{"key":"10.1007\/s40593-021-00269-9_bib37","doi-asserted-by":"crossref","unstructured":"Rasmussen, C. E. (2004). Gaussian processes in machine learning. In Advanced lectures on machine learning (pp. 63\u201371). Springer.","DOI":"10.1007\/978-3-540-28650-9_4"},{"issue":"4","key":"10.1007\/s40593-021-00269-9_bib38","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1080\/00220970209599510","article-title":"From example study to problem solving: Smooth transitions help learning","volume":"70","author":"Renkl","year":"2002","journal-title":"The Journal of Experimental Education"},{"key":"10.1007\/s40593-021-00269-9_bib39","doi-asserted-by":"crossref","unstructured":"Rowe, J., Mott, B., & Lester, J. (2014). Optimizing player experience in interactive narrative planning: a modular reinforcement learning approach. In Tenth artificial intelligence and interactive digital entertainment conference.","DOI":"10.1609\/aiide.v10i1.12733"},{"key":"10.1007\/s40593-021-00269-9_bib40","doi-asserted-by":"crossref","unstructured":"Rowe, J. P., & Lester, J. C. (2015). Improving student problem solving in narrative-centered learning environments: a modular reinforcement learning framework. In International conference on artificial intelligence in education (pp. 419\u2013428). Springer.","DOI":"10.1007\/978-3-319-19773-9_42"},{"key":"10.1007\/s40593-021-00269-9_bib41","unstructured":"Ryan, M., & Reid, M. (2000). Learning to fly: an application of hierarchical reinforcement learning. In Proceedings of the 17th international conference on machine learning. Citeseer."},{"issue":"3","key":"10.1007\/s40593-021-00269-9_bib42","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s11251-009-9107-8","article-title":"The expertise reversal effect and worked examples in tutored problem solving","volume":"38","author":"Salden","year":"2010","journal-title":"Instructional Science"},{"key":"10.1007\/s40593-021-00269-9_bib43","unstructured":"Schaul, T., Quan, J., Antonoglou, I., & Silver, D. (2015). Prioritized experience replay. arXiv:1511.05952."},{"key":"10.1007\/s40593-021-00269-9_bib44","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., & Moritz, P. (2015). Trust region policy optimization. In International conference on machine learning (pp. 1889\u20131897)."},{"key":"10.1007\/s40593-021-00269-9_bib45","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv:1707.06347."},{"issue":"9-10","key":"10.1007\/s40593-021-00269-9_bib46","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1007\/s10994-017-5650-8","article-title":"Offline reinforcement learning with task hierarchies","volume":"106","author":"Schwab","year":"2017","journal-title":"Machine Learning"},{"issue":"2","key":"10.1007\/s40593-021-00269-9_bib47","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.chb.2008.12.011","article-title":"The worked-example effect: Not an artefact of lousy control conditions","volume":"25","author":"Schwonke","year":"2009","journal-title":"Computers in Human Behavior"},{"key":"10.1007\/s40593-021-00269-9_bib48","doi-asserted-by":"crossref","unstructured":"Shen, S., Ausin, M. S., Mostafavi, B., & Chi, M. (2018). Improving learning & reducing time: a constrained action-based reinforcement learning approach. In Proceedings of the 26th conference on user modeling, adaptation and personalization (pp. 43\u201351). ACM.","DOI":"10.1145\/3209219.3209232"},{"key":"10.1007\/s40593-021-00269-9_bib49","doi-asserted-by":"crossref","unstructured":"Shen, S., & Chi, M. (2016). Reinforcement learning: the sooner the better, or the later the better?. In Proceedings of the 2016 conference on user modeling adaptation and personalization (pp. 37\u201344). ACM.","DOI":"10.1145\/2930238.2930247"},{"key":"10.1007\/s40593-021-00269-9_bib50","doi-asserted-by":"crossref","unstructured":"Shih, B., Koedinger, K. R., & Scheines, R. (2011). A response time model for bottom-out hints as worked examples. Handbook of educational data mining, 201\u2013212.","DOI":"10.1201\/b10274-17"},{"issue":"7587","key":"10.1007\/s40593-021-00269-9_bib51","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"issue":"6419","key":"10.1007\/s40593-021-00269-9_bib52","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1126\/science.aar6404","article-title":"A general reinforcement learning algorithm that masters chess, shogi, and go through self-play","volume":"362","author":"Silver","year":"2018","journal-title":"Science"},{"issue":"2","key":"10.1007\/s40593-021-00269-9_bib53","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1037\/0022-006X.59.2.205","article-title":"Aptitude-treatment interaction as a framework for research on individual differences in psychotherapy","volume":"59","author":"Snow","year":"1991","journal-title":"Journal of Consulting and Clinical Psychology"},{"key":"10.1007\/s40593-021-00269-9_bib54","doi-asserted-by":"crossref","unstructured":"Stamper, J. C., Eagle, M., Barnes, T., & Croy, M. (2011). Experimental evaluation of automatic hint generation for a logic tutor. In International conference on artificial intelligence in education (pp. 345\u2013352). Springer.","DOI":"10.1007\/978-3-642-21869-9_45"},{"issue":"1-2","key":"10.1007\/s40593-021-00269-9_bib55","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning","volume":"112","author":"Sutton","year":"1999","journal-title":"Artificial Intelligence"},{"issue":"1","key":"10.1007\/s40593-021-00269-9_bib56","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1207\/s1532690xci0201_3","article-title":"The use of worked examples as a substitute for problem solving in learning algebra","volume":"2","author":"Sweller","year":"1985","journal-title":"Cognition and Instruction"},{"issue":"1","key":"10.1007\/s40593-021-00269-9_bib57","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/BF01273901","article-title":"To know and to teach: Mathematical pedagogy from a historical context","volume":"29","author":"Swetz","year":"1995","journal-title":"Educational Studies in Mathematics"},{"key":"10.1007\/s40593-021-00269-9_bib58","unstructured":"Swetz, F. J. (1987). Capitalism and arithmetic: the new math of the 15th century, including the full text of the Treviso arithmetic of 1478, translated by David Eugene Smith Open Court Publishing."},{"issue":"3","key":"10.1007\/s40593-021-00269-9_bib59","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.cedpsych.2010.10.004","article-title":"Effects of worked examples, example-problem, and problem-example pairs on novices\u2019 learning","volume":"36","author":"Van Gog","year":"2011","journal-title":"Contemporary Educational Psychology"},{"key":"10.1007\/s40593-021-00269-9_bib60","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., & Silver, D. (2016). Deep reinforcement learning with double q-learning. In AAAI. Phoenix, AZ, (Vol. 2 p. 5).","DOI":"10.1609\/aaai.v30i1.10295"},{"issue":"3","key":"10.1007\/s40593-021-00269-9_bib61","first-page":"227","article-title":"The behavior of tutoring systems","volume":"16","author":"Vanlehn","year":"2006","journal-title":"IJAIED"},{"key":"10.1007\/s40593-021-00269-9_bib62","doi-asserted-by":"crossref","unstructured":"VanLehn, K., Bhembe, D., Chi, M., Lynch, C., Schulze, K., Shelby, R., Taylor, L., Treacy, D., Weinstein, A., & Wintersgill, M. (2004). Implicit versus explicit learning of strategies in a non-procedural cognitive skill. In International conference on intelligent tutoring systems (pp. 521\u2013530). Springer.","DOI":"10.1007\/978-3-540-30139-4_49"},{"key":"10.1007\/s40593-021-00269-9_bib63","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"key":"10.1007\/s40593-021-00269-9_bib64","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, W., Wu, J., Wang, Y. F., & Yang Wang, W. (2018). Video captioning via hierarchical reinforcement learning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4213\u20134222).","DOI":"10.1109\/CVPR.2018.00443"},{"key":"10.1007\/s40593-021-00269-9_bib65","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., & De Freitas, N. (2015). Dueling network architectures for deep reinforcement learning. arXiv:1511.06581."},{"key":"10.1007\/s40593-021-00269-9_bib66","doi-asserted-by":"crossref","unstructured":"Williams, J.D. (2008). The best of both worlds: unifying conventional dialog systems and pomdps. In INTERSPEECH (pp. 1173\u20131176).","DOI":"10.21437\/Interspeech.2008-355"},{"key":"10.1007\/s40593-021-00269-9_bib67","doi-asserted-by":"crossref","unstructured":"Zhou, G., Azizsoltani, H., Ausin, M. S., Barnes, T., & Chi, M. (2019). Hierarchical reinforcement learning for pedagogical policy induction. In International conference on artificial intelligence in education.","DOI":"10.1007\/978-3-030-23204-7_45"},{"key":"10.1007\/s40593-021-00269-9_bib68","unstructured":"Zhou, G., & Chi, M. (2017). The impact of decision agency & granularity on aptitude treatment interaction in tutoring. In Proceedings of the 39th annual conference of the cognitive science society (pp. 3652\u20133657)."},{"key":"10.1007\/s40593-021-00269-9_bib69","unstructured":"Zhou, G., Lynch, C., Price, T. W., Barnes, T., & Chi, M. (2016). The impact of granularity on the effectiveness of students\u2019 pedagogical decision. In Proceedings of the 38th annual conference of the cognitive science society (pp. 2801\u20132806)."},{"key":"10.1007\/s40593-021-00269-9_bib70","unstructured":"Zhou, G., Price, T. W., Lynch, C., Barnes, T., & Chi, M. (2015). The impact of granularity on worked examples and problem solving. In Proceedings of the 37th annual conference of the cognitive science society (pp. 2817\u20132822)."},{"key":"10.1007\/s40593-021-00269-9_bib71","unstructured":"Zhou, G., Wang, J., Lynch, C., & Chi, M. (2017). Towards closing the loop: Bridging machine-induced pedagogical policies to learning theories. In EDM."},{"key":"10.1007\/s40593-021-00269-9_bib72","doi-asserted-by":"crossref","unstructured":"Zhou, G., Yang, X., Azizsoltani, H., Barnes, T., & Chi, M. (2020). Improving student-tutor interaction through data-driven explanation of hierarchical reinforcement induced pedagogical policies. In Proceedings of the 28th conference on user modeling, adaptation and personalization. ACM.","DOI":"10.1145\/3340631.3394848"}],"container-title":["International Journal of Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-021-00269-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40593-021-00269-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1560429226002143?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1560429226002143?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-021-00269-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T06:15:06Z","timestamp":1779084906000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1560429226002143"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":72,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["S1560429226002143"],"URL":"https:\/\/doi.org\/10.1007\/s40593-021-00269-9","relation":{},"ISSN":["1560-4292"],"issn-type":[{"value":"1560-4292","type":"print"}],"subject":[],"published":{"date-parts":[[2022,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Leveraging Granularity: Hierarchical Reinforcement Learning for Pedagogical Policy Induction","name":"articletitle","label":"Article Title"},{"value":"International Journal of Artificial Intelligence in Education","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1007\/s40593-021-00269-9","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Copyright \u00a9 2021 International Artificial Intelligence in Education Society. Published by Elsevier Ltd","name":"copyright","label":"Copyright"}]}}