CSC News

January 27, 2020

Team Wins Best Paper Award at AIED 2019

Congratulations to NC State Computer Science PhD students Guojing Zhou and Markel Sanz Ausin, former postdoc Hamoon Azizsoltani (now at SAS), and professors Dr. Min Chi and Dr. Tiffany Barnes, for winning the Best Paper Award at the 20th International Conference on Artificial Intelligence in Education (AIED 2019) held in Chicago, IL June 25-29, 2019.


The winning paper is “Hierarchical Reinforcement Learning for Pedagogical Policy Induction.”  The abstract follows:


Abstract:  In interactive e-learning environments such as Intelligent Tutoring Systems, there are pedagogical decisions to make at two main levels of granularity: whole problems and single steps. Recent years have seen growing interest in data-driven techniques for such pedagogical decision making, which can dynamically tailor students’ learning experiences. Most existing data-driven approaches, however, treat these pedagogical decisions equally, or independently, disregarding the long-term impact that tutor decisions may have across these two levels of granularity. In this paper, we propose and apply an offline, off-policy Gaussian Processes based Hierarchical Reinforcement Learning (HRL) framework to induce a hierarchical pedagogical policy that makes decisions at both problem and step levels. In an empirical classroom study with 180 students, our results show that the HRL policy is significantly more effective than a Deep Q-Network (DQN) induced policy and a random yet reasonable baseline policy.


To read the winning paper, click here.


The theme for the AIED 2019 conference was “Education for All in the XXI Century”. Inequity within and between countries continues to grow in the industrial age. Intelligent information technologies have been proposed to reduce this difference but may instead increase the digital divide if applied without reflection. Education plays a central role in this problem, as it is one of the key approaches that could help to reduce this difference. However, further work is needed to understand how to provide equitable education for all, and many questions remain to be answered. What are the main barriers to providing educational opportunities to underserved teachers and learners? How can AI and advanced technologies help overcome these difficulties? How can this work be done ethically? In this conference we gathered the collective intelligence of the community to think about this problem and provide innovative and creative solutions.



Return To News Homepage