{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T16:45:03Z","timestamp":1779122703933,"version":"3.51.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030782917","type":"print"},{"value":"9783030782924","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-78292-4_29","type":"book-chapter","created":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T21:03:59Z","timestamp":1623359039000},"page":"356-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Tackling the Credit Assignment Problem in Reinforcement Learning-Induced Pedagogical Policies with Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4526-9252","authenticated-orcid":false,"given":"Markel Sanz","family":"Ausin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehak","family":"Maniktala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiffany","family":"Barnes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1765-7837","authenticated-orcid":false,"given":"Min","family":"Chi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,11]]},"reference":[{"key":"29_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E.: TensorFlow: arge-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/, software available from tensorflow.org"},{"key":"29_CR2","unstructured":"Andrychowicz, M., Baker, B., et al.: Learning dexterous in-hand manipulation. arXiv:1808.00177 (2018)"},{"key":"29_CR3","unstructured":"Ausin, M.S.: Leveraging deep reinforcement learning for pedagogical policy induction in an intelligent tutoring system. In: Proceedings of the 12th International Conference on Educational Data Mining (EDM 2019) (2019)"},{"key":"29_CR4","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-52237-7_38","volume-title":"Artificial Intelligence in Education","author":"M Sanz Ausin","year":"2020","unstructured":"Sanz Ausin, M., Maniktala, M., Barnes, T., Chi, M.: Exploring the impact of simple explanations and agency on batch deep reinforcement learning induced pedagogical policies. In: Bittencourt, I.I., Cukurova, M., Muldner, K., Luckin, R., Mill\u00e1n, E. (eds.) AIED 2020. LNCS (LNAI), vol. 12163, pp. 472\u2013485. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-52237-7_38"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Azizsoltani, H., et al.: Unobserved is not equal to non-existent: using gaussian processes to infer immediate rewards across contexts. In: Proceedings of the 28th IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/273"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Chen, B., Xu, M., Li, L., Zhao, D.: Delay-aware model-based reinforcement learning for continuous control. arXiv preprint arXiv:2005.05440 (2020)","DOI":"10.1016\/j.neucom.2021.04.015"},{"issue":"1\u20132","key":"29_CR7","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s11257-010-9093-1","volume":"21","author":"M Chi","year":"2011","unstructured":"Chi, M., VanLehn, K., Litman, D., Jordan, P.: Empirically evaluating the application of reinforcement learning to the induction of effective and adaptive pedagogical strategies. User Model. User-Adapted Interact. 21(1\u20132), 137\u2013180 (2011)","journal-title":"User Model. User-Adapted Interact."},{"key":"29_CR8","unstructured":"Chollet, F.: Keras. https:\/\/keras.io (2015)"},{"issue":"8","key":"29_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"1","key":"29_CR10","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10489-008-0115-1","volume":"31","author":"A Iglesias","year":"2009","unstructured":"Iglesias, A., Mart\u00ednez, P., Aler, R., Fern\u00e1ndez, F.: Learning teaching strategies in an adaptive and intelligent educational system through reinforcement learning. Appl. Intell 31(1), 89\u2013106 (2009)","journal-title":"Appl. Intell"},{"issue":"4","key":"29_CR11","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1016\/j.knosys.2009.01.007","volume":"22","author":"A Iglesias","year":"2009","unstructured":"Iglesias, A., Mart\u00ednez, P., Aler, R., Fern\u00e1ndez, F.: Reinforcement learning of pedagogical policies in adaptive and intelligent educational systems. Knowl.-Based Syst. 22(4), 266\u2013270 (2009)","journal-title":"Knowl.-Based Syst."},{"key":"29_CR12","unstructured":"Ju, S., Chi, M., Zhou, G.: Pick the moment: identifying critical pedagogical decisions using long-short term rewards. In: Rafferty, A.N., Whitehill, J., Romero, C., Cavalli-Sforza, V. (eds.) Proceedings of the 13th International Conference on Educational Data Mining, EDM 2020, Fully Virtual Conference, 10\u201313 July 2020. International Educational Data Mining Society (2020). https:\/\/educationaldatamining.org\/files\/conferences\/EDM2020\/papers\/paper_167.pdf"},{"key":"29_CR13","unstructured":"Ju, S., Zhou, G., Azizsoltani, H., Barnes, T., Chi, M.: Identifying critical pedagogical decisions through adversarial deep reinforcement learning. In: EDM International Educational Data Mining Society (IEDMS) (2019)"},{"key":"29_CR14","first-page":"30","volume":"8","author":"KR Koedinger","year":"1997","unstructured":"Koedinger, K.R., Anderson, J.R., Hadley, W.H., Mark, M.A.: Intelligent tutoring goes to school in the big city. Int. J. Artif. Intell. Educ. (IJAIED) 8, 30\u201343 (1997)","journal-title":"Int. J. Artif. Intell. Educ. (IJAIED)"},{"key":"29_CR15","unstructured":"Mandel, T., Liu, Y.E., Levine, S., Brunskill, E., Popovic, Z.: Offline policy evaluation across representations with applications to educational games. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, pp. 1077\u20131084. International Foundation for Autonomous Agents and Multiagent Systems (2014)"},{"key":"29_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/978-3-319-07221-0_44","volume-title":"Intelligent Tutoring Systems","author":"BM McLaren","year":"2014","unstructured":"McLaren, B.M., van Gog, T., Ganoe, C., Yaron, D., Karabinos, M.: Exploring the assistance dilemma: comparing instructional support in examples and problems. In: Trausan-Matu, S., Boyer, K.E., Crosby, M., Panourgia, K. (eds.) ITS 2014. LNCS, vol. 8474, pp. 354\u2013361. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-07221-0_44"},{"key":"29_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/978-3-642-21869-9_30","volume-title":"Artificial Intelligence in Education","author":"BM McLaren","year":"2011","unstructured":"McLaren, B.M., Isotani, S.: When is it best to learn with all worked examples? In: Biswas, G., Bull, S., Kay, J., Mitrovic, A. (eds.) AIED 2011. LNCS (LNAI), vol. 6738, pp. 222\u2013229. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-21869-9_30"},{"key":"29_CR18","unstructured":"McLaren, B.M., Lim, S.J., Koedinger, K.R.: When and how often should worked examples be given to students? New results and a summary of the current state of research. In: Proceedings of the 30th Annual Conference of the Cognitive Science Society, pp. 2176\u20132181 (2008)"},{"key":"29_CR19","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/JRPROC.1961.287775","volume":"49","author":"M Minsky","year":"1961","unstructured":"Minsky, M.: Steps toward artificial intelligence. Proc. IRE 49, 8\u201330 (1961)","journal-title":"Proc. IRE"},{"issue":"7540","key":"29_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"issue":"5","key":"29_CR21","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/s11257-016-9181-y","volume":"26","author":"AS Najar","year":"2016","unstructured":"Najar, A.S., Mitrovic, A., McLaren, B.M.: Learning with intelligent tutors and worked examples: selecting learning activities adaptively leads to better learning outcomes than a fixed curriculum. User Model. User-Adapted Interact. 26(5), 459\u2013491 (2016). https:\/\/doi.org\/10.1007\/s11257-016-9181-y","journal-title":"User Model. User-Adapted Interact."},{"issue":"6","key":"29_CR22","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1111\/cogs.12290","volume":"40","author":"AN Rafferty","year":"2016","unstructured":"Rafferty, A.N., Brunskill, E., et al.: Faster teaching via pomdp planning. Cognit. Sci. 40(6), 1290\u20131332 (2016)","journal-title":"Cognit. Sci."},{"issue":"4","key":"29_CR23","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1080\/00220970209599510","volume":"70","author":"A Renkl","year":"2002","unstructured":"Renkl, A., Atkinson, R.K., et al.: From example study to problem solving: smooth transitions help learning. J. Exp. Educ. 70(4), 293\u2013315 (2002)","journal-title":"J. Exp. Educ."},{"issue":"3","key":"29_CR24","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s11251-009-9107-8","volume":"38","author":"RJ Salden","year":"2010","unstructured":"Salden, R.J., Aleven, V., Schwonke, R., Renkl, A.: The expertise reversal effect and worked examples in tutored problem solving. Instr. Sci. 38(3), 289\u2013307 (2010)","journal-title":"Instr. Sci."},{"issue":"9","key":"29_CR25","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1007\/s10994-017-5650-8","volume":"106","author":"D Schwab","year":"2017","unstructured":"Schwab, D., Ray, S.: Offline reinforcement learning with task hierarchies. Mach. Learn. 106(9), 1569\u20131598 (2017). https:\/\/doi.org\/10.1007\/s10994-017-5650-8","journal-title":"Mach. Learn."},{"issue":"2","key":"29_CR26","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.chb.2008.12.011","volume":"25","author":"R Schwonke","year":"2009","unstructured":"Schwonke, R., Renkl, A., Krieg, C., Wittwer, J., Aleven, V., Salden, R.: The worked-example effect: not an artefact of lousy control conditions. Comput. Hum. Behav. 25(2), 258\u2013266 (2009)","journal-title":"Comput. Hum. Behav."},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Shen, S., Ausin, M.S., Mostafavi, B., Chi, M.: Improving learning & reducing time: a constrained action-based reinforcement learning approach. In: UMAP, pp. 43\u201351. ACM (2018)","DOI":"10.1145\/3209219.3209232"},{"key":"29_CR28","unstructured":"Shen, S., Chi, M.: Aim Low: Correlation-based Feature Selection for Model-based Reinforcement Learning. International Educational Data Mining Society (2016)"},{"key":"29_CR29","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":"29_CR30","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/978-3-319-93846-2_61","volume-title":"Artificial Intelligence in Education","author":"S Shen","year":"2018","unstructured":"Shen, S., Mostafavi, B., Lynch, C., Barnes, T., Chi, M.: Empirically evaluating the effectiveness of pomdp vs. mdp towards the pedagogical strategies induction. In: Penstein Ros\u00e9, C., et al. (eds.) AIED 2018. LNCS (LNAI), vol. 10948, pp. 327\u2013331. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93846-2_61"},{"issue":"7587","key":"29_CR31","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484 (2016)","journal-title":"Nature"},{"issue":"6419","key":"29_CR32","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"issue":"1","key":"29_CR33","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3(1), 9\u201344 (1988)","journal-title":"Mach. Learn."},{"issue":"1","key":"29_CR34","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1207\/s1532690xci0201_3","volume":"2","author":"J Sweller","year":"1985","unstructured":"Sweller, J., Cooper, G.A.: The use of worked examples as a substitute for problem solving in learning algebra. Cognit. Instr. 2(1), 59\u201389 (1985)","journal-title":"Cognit. Instr."},{"issue":"1","key":"29_CR35","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1080\/03640210709336984","volume":"31","author":"K VanLehn","year":"2007","unstructured":"VanLehn, K., Graesser, A.C., et al.: When are tutorial dialogues more effective than reading? Cognit. Sci. 31(1), 3\u201362 (2007)","journal-title":"Cognit. Sci."},{"key":"29_CR36","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W., et al.: Grandmaster level in StarCraft ii using multi-agent reinforcement learning. Nature 575, 350 (2019)","journal-title":"Nature"},{"key":"29_CR37","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":"29_CR38","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv:1511.06581 (2015)"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, G., Azizsoltani, H., Ausin, M.S., Barnes, T., Chi, M.: Hierarchical reinforcement learning for pedagogical policy induction (extended abstract). In: IJCAI, pp. 4691\u20134695. ijcai.org (2020)","DOI":"10.24963\/ijcai.2020\/647"}],"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\/978-3-030-78292-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T21:12:19Z","timestamp":1623359539000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-78292-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030782917","9783030782924"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-78292-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"11 June 2021","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":"Utrecht","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2021.science.uu.nl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"209","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"76","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"19% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}