Reinforcement Learning for the Adaptive Scheduling of Educational Activities

要旨

Adaptive instruction for online education can increase learning gains and decrease the work required of learners, instructors, and course designers. Reinforcement Learning (RL) is a promising tool for developing instructional policies, as RL models can learn complex relationships between course activities, learner actions, and educational outcomes. This paper demonstrates the first RL model to schedule educational activities in real time for a large online course through active learning. Our model learns to assign a sequence of course activities while maximizing learning gains and minimizing the number of items assigned. Using a controlled experiment with over 1,000 learners, we investigate how this scheduling policy affects learning gains, dropout rates, and qualitative learner feedback. We show that our model produces better learning gains using fewer educational activities than a linear assignment condition, and produces similar learning gains to a self-directed condition using fewer educational activities and with lower dropout rates.

受賞
Honorable Mention
キーワード
Online education
adaptive learning
reinforcement learning
著者
Jonathan Bassen
Stanford University, Stanford, CA, USA
Bharathan Balaji
Amazon, Seattle, WA, USA
Michael Schaarschmidt
University of Cambridge, Cambridge, United Kingdom
Candace Thille
Amazon, Seattle, WA, USA
Jay Painter
Amazon, Seattle, WA, USA
Dawn Zimmaro
Amazon, Seattle, WA, USA
Alex Games
Amazon, Seattle, WA, USA
Ethan Fast
Stanford University, Stanford, CA, USA
John C. Mitchell
Stanford University, Stanford, CA, USA
DOI

10.1145/3313831.3376518

論文URL

https://doi.org/10.1145/3313831.3376518

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: Tutoring & learning

Paper session
313A O'AHU
5 件の発表
2020-04-27 20:00:00
2020-04-27 21:15:00
日本語まとめ
読み込み中…