{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:43:36Z","timestamp":1782405816565,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T00:00:00Z","timestamp":1587427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007515","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1176927-100-QCADX"],"award-info":[{"award-number":["1176927-100-QCADX"]}],"id":[{"id":"10.13039\/100007515","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,4,21]]},"DOI":"10.1145\/3313831.3376518","type":"proceedings-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T16:16:47Z","timestamp":1590596207000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":52,"title":["Reinforcement Learning for the Adaptive Scheduling of Educational Activities"],"prefix":"10.1145","author":[{"given":"Jonathan","family":"Bassen","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bharathan","family":"Balaji","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Schaarschmidt","sequence":"additional","affiliation":[{"name":"University of Cambridge, Cambridge, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Candace","family":"Thille","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay","family":"Painter","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawn","family":"Zimmaro","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Games","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ethan","family":"Fast","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John C.","family":"Mitchell","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,4,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3231644.3231669"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_1_3_1","volume-title":"Openai gym. arXiv preprint arXiv:1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. Openai gym. arXiv preprint arXiv:1606.01540 (2016)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 9th International Conference of the Learning Sciences-Volume 1. International Society of the Learning Sciences, 153--160","author":"Chase Catherine C","year":"2010","unstructured":"Catherine C Chase, Jonathan T Shemwell, and Daniel L Schwartz. 2010. Explaining across contrasting cases for deep understanding in science: An example using interactive simulations. In Proceedings of the 9th International Conference of the Learning Sciences-Volume 1. International Society of the Learning Sciences, 153--160."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01099821"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3051457.3051463"},{"key":"e_1_3_2_1_7_1","volume-title":"Doubly robust policy evaluation and learning. arXiv preprint arXiv:1103.4601","author":"Dud\u00edk Miroslav","year":"2011","unstructured":"Miroslav Dud\u00edk, John Langford, and Lihong Li. 2011. Doubly robust policy evaluation and learning. arXiv preprint arXiv:1103.4601 (2011)."},{"key":"e_1_3_2_1_8_1","volume-title":"Handbook of competence and motivation","author":"Elliot Andrew J","unstructured":"Andrew J Elliot and Carol S Dweck. 2013. Handbook of competence and motivation. Guilford Publications."},{"key":"e_1_3_2_1_9_1","volume-title":"Structure-Mapping: A Theoretical Framework for Analogy. Cognitive science 7, 2","author":"Gentner Dedre","year":"1983","unstructured":"Dedre Gentner. 1983. Structure-Mapping: A Theoretical Framework for Analogy. Cognitive science 7, 2 (1983), 155--170."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2820011"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research), Jennifer Dy and Andreas Krause (Eds.)","volume":"80","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 Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research), Jennifer Dy and Andreas Krause (Eds.), Vol. 80. PMLR, Stockholmsm\u00c3d'ssan, Stockholm Sweden, 1861--1870. http:\/\/proceedings.mlr.press\/v80\/haarnoja18b.html"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-014-0024-x"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the twentieth annual conference of the cognitive science society","author":"Heffernan Neil T","year":"1998","unstructured":"Neil T Heffernan and Kenneth R Koedinger. 1998. A developmental model for algebra symbolization: The results of a difficulty factors assessment. In Proceedings of the twentieth annual conference of the cognitive science society. Hillsdale, NJ, 484--489."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2009.01.007"},{"key":"e_1_3_2_1_15_1","volume-title":"Integrating Knowledge Tracing and Item Response Theory: A Tale of Two Frameworks. In UMAP Workshops.","author":"Khajah Mohammad","year":"2014","unstructured":"Mohammad Khajah, Yun Huang, Jos\u00e9 P. Gonz\u00e1lez-Brenes, Michael C. Mozer, and Peter Brusilovsky. 2014. Integrating Knowledge Tracing and Item Response Theory: A Tale of Two Frameworks. In UMAP Workshops."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556325.2566237"},{"key":"e_1_3_2_1_17_1","volume-title":"John Stamper, Tristan Nixon, and Steven Ritter.","author":"Koedinger Kenneth","year":"2010","unstructured":"Kenneth Koedinger, Philip I Pavlik Jr, John Stamper, Tristan Nixon, and Steven Ritter. 2010. Avoiding problem selection thrashing with conjunctive knowledge tracing. In Educational data mining 2011."},{"key":"e_1_3_2_1_18_1","volume-title":"The Knowledge-Learning-Instruction framework: Bridging the science-practice chasm to enhance robust student learning. Cognitive science 36, 5","author":"Koedinger Kenneth R","year":"2012","unstructured":"Kenneth R Koedinger, Albert T Corbett, and Charles Perfetti. 2012. The Knowledge-Learning-Instruction framework: Bridging the science-practice chasm to enhance robust student learning. Cognitive science 36, 5 (2012), 757--798."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505057"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2724660.2724670"},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in Neural Information Processing Systems 26","author":"Lindsey Robert V","unstructured":"Robert V Lindsey, Michael C Mozer, William J Huggins, and Harold Pashler. 2013. Optimizing Instructional Policies. In Advances in Neural Information Processing Systems 26, C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 2778--2786. http:\/\/papers.nips.cc\/paper\/4887-optimizing-instructional-policies.pdf"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557392"},{"key":"e_1_3_2_1_23_1","unstructured":"Yun-En Liu Travis Mandel Emma Brunskill and Zoran Popovic. 2014b. Trading Off Scientific Knowledge and User Learning with Multi-Armed Bandits.. In EDM. 161--168."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems, 1077--1084","author":"Mandel Travis","year":"2014","unstructured":"Travis Mandel, Yun-En Liu, Sergey Levine, Emma Brunskill, and Zoran Popovic. 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, 1077--1084."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2724660.2728683"},{"key":"e_1_3_2_1_26_1","volume-title":"Mechanisms of skill acquisition and the law of practice. Cognitive skills and their acquisition 1","author":"Newell Allen","year":"1981","unstructured":"Allen Newell and Paul S Rosenbloom. 1981. Mechanisms of skill acquisition and the law of practice. Cognitive skills and their acquisition 1, 1981 (1981), 1--55."},{"key":"e_1_3_2_1_27_1","unstructured":"Chris Piech Jonathan Bassen Jonathan Huang Surya Ganguli Mehran Sahami Leonidas J Guibas and Jascha Sohl-Dickstein. 2015. Deep knowledge tracing. In Advances in neural information processing systems. 505--513."},{"key":"e_1_3_2_1_28_1","volume-title":"Foundations of intelligent tutoring systems","author":"Polson Martha C","unstructured":"Martha C Polson and J Jeffrey Richardson. 2013. Foundations of intelligent tutoring systems. Psychology Press."},{"key":"e_1_3_2_1_29_1","unstructured":"J. vanMarrienboer K. Yates R. Clark D. Feldon and S. Early. 2008. Handbook of research on educational communications and technology (3rd ed.). Chapter Cognitive task analysis for training 577--593."},{"key":"e_1_3_2_1_30_1","unstructured":"Georg Rasch. 1960. Studies in mathematical psychology: I. Probabilistic models for some intelligence and attainment tests. (1960)."},{"key":"e_1_3_2_1_31_1","volume-title":"The effects of spacing and mixing practice problems. Journal for Research in Mathematics Education","author":"Rohrer Doug","year":"2009","unstructured":"Doug Rohrer. 2009. The effects of spacing and mixing practice problems. Journal for Research in Mathematics Education (2009), 4--17."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 2nd Conference on Systems and Machine Learning (SysML).","author":"Schaarschmidt Michael","year":"2019","unstructured":"Michael Schaarschmidt, Sven Mika, Kai Fricke, and Eiko Yoneki. 2019. RLgraph: Modular Computation Graphs for Deep Reinforcement Learning. In Proceedings of the 2nd Conference on Systems and Machine Learning (SysML)."},{"key":"e_1_3_2_1_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_1_34_1","volume-title":"Joseph Jay Williams, Kobi Gal, and Yaar Shalom.","author":"Segal Avi","year":"2018","unstructured":"Avi Segal, Yossi Ben David, Joseph Jay Williams, Kobi Gal, and Yaar Shalom. 2018. Combining Difficulty Ranking with Multi-Armed Bandits to Sequence Educational Content. In Artificial Intelligence in Education, Carolyn Penstein Ros\u00e9, Roberto Mart\u00ednez-Maldonado, H. Ulrich Hoppe, Rose Luckin, Manolis Mavrikis, Kaska Porayska-Pomsta, Bruce McLaren, and Benedict du Boulay (Eds.). Springer International Publishing, Cham, 317--321."},{"key":"e_1_3_2_1_35_1","volume-title":"Architecture of knowledge structures and cognitive diagnosis: A statistical pattern recognition and classification approach. Cognitively diagnostic assessment","author":"Tatsuoka Kikumi K","year":"1995","unstructured":"Kikumi K Tatsuoka. 1995. Architecture of knowledge structures and cognitive diagnosis: A statistical pattern recognition and classification approach. Cognitively diagnostic assessment (1995), 327--359."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"J. Sewall V. Aleven B. McLaren and K. Koedinger. 2006. The cognitive tutor authoring tools (CTAT): preliminary evaluation of efficiency gains. In Intelligent Tutoring Systems (ITS '06). 61--70.","DOI":"10.1007\/11774303_7"},{"key":"e_1_3_2_1_37_1","volume-title":"Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Remi Munos, Koray Kavukcuoglu, and Nando de Freitas. 2016. Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224 (2016)."},{"key":"e_1_3_2_1_38_1","volume-title":"Machine learning 8, 3--4","author":"Watkins Christopher JCH","year":"1992","unstructured":"Christopher JCH Watkins and Peter Dayan. 1992. Q-learning. Machine learning 8, 3--4 (1992), 279--292."},{"key":"e_1_3_2_1_39_1","volume-title":"Beyond prediction: First steps toward automatic intervention in MOOC student stopout. Available at SSRN 2611750","author":"Whitehill Jacob","year":"2015","unstructured":"Jacob Whitehill, Joseph Williams, Glenn Lopez, Cody Coleman, and Justin Reich. 2015. Beyond prediction: First steps toward automatic intervention in MOOC student stopout. Available at SSRN 2611750 (2015)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2876034.2876042"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173781"}],"event":{"name":"CHI '20: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '20","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3313831.3376518","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3313831.3376518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:32:52Z","timestamp":1750199572000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3313831.3376518"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,21]]},"references-count":41,"alternative-id":["10.1145\/3313831.3376518","10.1145\/3313831"],"URL":"https:\/\/doi.org\/10.1145\/3313831.3376518","relation":{},"subject":[],"published":{"date-parts":[[2020,4,21]]},"assertion":[{"value":"2020-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}