*******************************************
SPEAKER: Simon Woodhead, Eedi (London, UK)
TITLE: Eedi Research - Open Data and a Platform for Running Experiments

ABSTRACT: Following on from the release of a award-winning, large-scale educational dataset, and hosting a competition at NeurIPS 2020, Eedi have been funded by Schmidt Futures to instrument their platform for researchers. Hear how we are adding functionality to allow experiments to be run within Eedi, what this means for Reinforcement Learning, and how you can use Eedi in your research.

BIO: Co-founder and PhD data scientist in the educational technology sector, creating award-winning edtech solutions through innovative data capture, analysis and visualisation. Senior executive of three edtech companies, with extensive knowledge of product and business development. Established success in turning ideas into reality, taking concepts from inception, through minimal viable products, to established successful solutions. Currently focused on optimising the pipeline between cutting-edge machine learning research and product enhancement.

*******************************************
SPEAKER: Manuel Lopes, Instituto Superior Tecnico (Lisbon, Portugal)
TITLE: Learning and Teaching in Markov Decision Problems

ABSTRACT: Learning is an interactive process between a learner and an environment that in social animals contains peers. We will show how the learning process can be improved if teachers and learners create a shared understanding of their mutual learning process. With active learners and understanding teachers, learning can be made much faster in situations of multiple heterogeneous students, and when the teachers lack some knowledge about the learning process of students.

BIO: Manuel Lopes is an associate professor at Instituto Superior Tecnico at the University of Lisbon. His research focuses on understanding the processes of natural and artificial learning. Understanding learning gives amazing insights into the human nature and will allow developing technologies to improve our well-being. To this end, I develop models of learning in animals and develop new learning methodologies for machines. His research contributions have included computational models of learning, new learning methods, and methods for human-machine collaboration, many times with robots.

*******************************************
SPEAKER: Tanja Kaser, EPFL (Lausanne, Switzerland)
TITLE: Modeling and Individualizing Learning in Open-Ended Learning Environments

ABSTRACT: Open-ended learning environments (OELEs) allow students to freely interact with the content and to ideally discover important principles and concepts of the learning domain on their own. Effectively using such environments is challenging for many students and therefore, adaptive guidance has the potential to improve student learning. Guidance in the form of targeted interventions or feedback therefore has the potential to improve educational outcomes. Providing effective support is, however, also a challenge because it is not clear how effective learning strategies in such environments look like. In this talk, I will first present examples for the early prediction of learning outcomes in educational games and interactive simulations. In the second part, I will focus on the use of RL agents in OELEs as a basis for understanding and intervention.

BIO: Tanja Kaser is an assistant professor at the School of Computer and Communication Sciences (IC) at EPFL. Her research lies at the intersection of machine learning, data mining, and education. She is particularly interested in creating accurate models of human behavior and learning. Prior to joining EPFL, Tanja Kaser was a senior data scientist with the Swiss Data Science Center at ETH Zurich. Before that, she was a postdoctoral researcher with the AAALab at the Graduate School of Education of Stanford University. Tanja Kaser received her PhD degree from the Computer Science Department of ETH Zurich; her thesis was distinguished with the Fritz Kutter Award for the best Computer Science thesis at a Swiss university.

*******************************************
SPEAKER: Thomas W. Price, North Carolina State University (Raleigh, NC, USA)
TITLE: Computing Education: Challenges, Opportunities and Approaches for Data-driven AI

ABSTRACT: Computer Science (CS) courses are growing at the K12 and university level, reflecting growing demand for computational skills across many fields. However, programming is a challenging skill to learn, and teachers are not always available to support students that are struggling. In this talk, I will demonstrate how we can address this challenge by building programming environments that support novice learners automatically with help features, like hints, feedback and examples, that adapt to a student's current code. I will highlight the research opportunities of working with rich programming data, and how it can be used to automate student support, as well as to predict student learning outcomes, and to inform curricular design. I will also discuss open questions and challenges in this research space, and exciting opportunities for applying reinforcement learning approaches to address these challenges.

BIO: Thomas Price is an Assistant Professor of Computer Science at North Carolina State University. His primary research goal is to develop learning environments that automatically support students through AI and data-driven help features. His work has focused on the domain of computing education, where he has developed techniques for automatically generating programming hints and feedback for students in real-time by leveraging student data. His HINTS lab focuses on supporting students working in creative, open-ended and block-based learning contexts, leading to novel data-driven programming support, including adaptive examples, subgoal feedback, and models to predict student outcomes.

*******************************************
SPEAKER: Mark Ho, Princeton University (Princeton, NJ, USA)
TITLE: Bridging Reinforcement Learning and Intuitive Pedagogy

ABSTRACT: Whether playing the role of teacher or learner, people enter into pedagogical interactions with a wealth of background assumptions and intuitive expectations. What do these look like? How should it inform the design of reinforcement learning systems involved in education? I will discuss several experiments that attempt to characterize how people playing the role of a teacher understand evaluative feedback (e.g., positive or negative feedback). A consistent finding is that people understand evaluative feedback to include a message about a target behavior and that such feedback is sensitive to the context of a learner's expertise. More broadly, such findings indicate that when applying reinforcement learning to education, it will be crucial to understand how people understand and reason about context-sensitive pedagogical goals.

BIO: Dr. Mark K Ho studies how the computational principles underlying human decision-making and social cognition can be used to inform the design of artificial intelligence systems. His research combines ideas from cognitive psychology and computer science to identify design principles for interactive agents and to build better models of how people think, act, and interact. Mark is currently a postdoctoral researcher in the Computer Science and Psychology departments at Princeton University. He received a Ph.D. in Cognitive Science and a M.S. in Computer Science from Brown University and a B.A. in Philosophy from Princeton University.

*******************************************
SPEAKER: Ethan Prihar, Worcester Polytechnic Institute (Worcester, MA, USA)
TITLE: Attempting to Personalize at Scale using Multi-Armed Bandit Algorithms

ABSTRACT: In this presentation we present the Automatic Personalized Learning Service (APLS). The APLS uses multi-armed bandit algorithms to recommend the most effective support to each student that requests assistance when completing their online work, and is currently used by ASSISTments, an online learning platform. The first empirical study of the APLS found that Beta-Bernoulli Thompson Sampling, a popular and effective multi-armed bandit algorithm, was only slightly more capable of selecting helpful support than randomly selecting from the relevant support options. Therefore, we also present Decision Tree Thompson Sampling (DTTS), a novel contextual multi-armed bandit algorithm that integrates the transparency and interpretability of decision trees into Thomson sampling. In simulation, DTTS overcame the challenges of recommending support within an online learning platform and was able to increase students' learning by as much as 10\% more than the current algorithm used by the APLS.

BIO: Ethan Prihar is a PhD Student at Worcester Polytechnic Institute in the ASSISTments Lab. His focus is on developing algorithms to personalize the tutoring students receive when struggling on their assignments and the infrastructure to support these algorithms within ASSISTments.

*******************************************