{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:52:59Z","timestamp":1743094379202,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031363351"},{"type":"electronic","value":"9783031363368"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-36336-8_93","type":"book-chapter","created":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T14:02:43Z","timestamp":1688047363000},"page":"599-605","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Unified Batch Hierarchical Reinforcement Learning Framework for\u00a0Pedagogical Policy Induction with\u00a0Deep Bisimulation Metrics"],"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7157-7283","authenticated-orcid":false,"given":"Mark","family":"Abdelshiheed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6500-9976","authenticated-orcid":false,"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":[[2023,6,30]]},"reference":[{"key":"93_CR1","unstructured":"Singla et al., A.: Reinforcement learning for education: Opportunities and challenges. arXiv preprint arXiv:2107.08828 (2021)"},{"key":"93_CR2","unstructured":"Zhang et al., A.: Learning invariant representations for reinforcement learning without reconstruction. arXiv preprint arXiv:2006.10742 (2020)"},{"key":"93_CR3","unstructured":"D\u2019Eramo et al., C.: Sharing knowledge in multi-task deep reinforcement learning. In: ICLR (2019)"},{"key":"93_CR4","unstructured":"Hafner et al., D.: Dream to control: Learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603 (2019)"},{"key":"93_CR5","unstructured":"Borsa et al., D.: Learning shared representations in multi-task reinforcement learning. arXiv preprint arXiv:1603.02041 (2016)"},{"key":"93_CR6","unstructured":"Higgins et al., I.: Darla: Improving zero-shot transfer in reinforcement learning. In: ICML, pp. 1480\u20131490. PMLR (2017)"},{"key":"93_CR7","unstructured":"Wang et al., K.: Improving generalization in reinforcement learning with mixture regularization. arXiv preprint arXiv:2010.10814 (2020)"},{"key":"93_CR8","unstructured":"Koedinger et al., K.R.: Intelligent tutoring goes to school in the big city. IJAIED 8, 30\u201343 (1997)"},{"key":"93_CR9","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":"93_CR10","doi-asserted-by":"crossref","unstructured":"Geden et al., M.: Predictive student modeling in educational games with multi-task learning. In: AAAI. vol. 34, pp. 654\u2013661 (2020)","DOI":"10.1609\/aaai.v34i01.5406"},{"key":"93_CR11","doi-asserted-by":"crossref","unstructured":"Ferns et al., N.: Bisimulation metrics for continuous mdps. SIAM 40(6), 1662\u20131714 (2011)","DOI":"10.1137\/10080484X"},{"key":"93_CR12","unstructured":"Sodhani et al., S.: Multi-task reinforcement learning with context-based representations. arXiv preprint arXiv:2102.06177 (2021)"},{"key":"93_CR13","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"},{"key":"93_CR14","unstructured":"Bram et al., T.: Attentive multi-task deep reinforcement learning. Preprint arXiv:1907.02874 (2019)"},{"key":"93_CR15","unstructured":"Mnih et al., V.: Playing atari with deep reinforcement learning. NIPS (2013)"},{"key":"93_CR16","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. Preprint arXiv:1312.6114 (2013)"},{"issue":"1","key":"93_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0890-5401(91)90030-6","volume":"94","author":"KG Larsen","year":"1991","unstructured":"Larsen, K.G., Skou, A.: Bisimulation through probabilistic testing. Inf. Comput. 94(1), 1\u201328 (1991)","journal-title":"Inf. Comput."},{"issue":"6","key":"93_CR18","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. Cogn. Sci. 40(6), 1290\u20131332 (2016)","journal-title":"Cogn. Sci."},{"issue":"3","key":"93_CR19","first-page":"227","volume":"16","author":"K Vanlehn","year":"2006","unstructured":"Vanlehn, K.: The behavior of tutoring systems. Int. J. Artif. Intell. Educ. 16(3), 227\u2013265 (2006)","journal-title":"Int. J. Artif. Intell. Educ."}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-36336-8_93","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T14:10:34Z","timestamp":1688047834000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-36336-8_93"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031363351","9783031363368"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-36336-8_93","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 June 2023","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":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.aied2023.org\/","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":"311","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":"53","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":"26","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":"17% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}