Schedule and Information
- Location: Workshop as part of the EDM'21 conference (virtual event).
- Date: 29 June, 2021.
- Schedule and information for attending the workshop: Full details are available here.
- Title+Abstract for invited talks: Full details are available here.
- List of spotlight presentations: See more information below in Spotlights.
- Contact: For any questions, please email rl4edorg AT gmail
- Updates:
- 2021-07-03: We have added recordings for talks and spotlights, see below.
- 2021-06-26: We have updated the schedule and information for attending the workshop.
- 2021-06-26: We have added details about the invited talks and presentations.
- 2021-05-15: We have updated the list of invited talks.
- 2021-04-25: RL4ED workshop will be a virtual event. More details will be provided soon.
- 2021-04-25: EDM'21 conference registration is now open.
Overview
This workshop aims to bring together researchers and practitioners interested in the broad areas of reinforcement learning (RL) and education (ED). The workshop will focus on two thrusts:
- Exploring how we can leverage recent advances in RL methods to improve the state-of-the art technology for ED.
- Identifying unique challenges in ED that are beyond the current methodology, but can help nurture technical innovations and next breakthroughs in RL.
Invited Talks
The workshop will have invited talks from seven speakers. Each of these talks will be about 25 mins; additionally, we will have two panel discussions with the speakers. You can find more details on the information page for talks and the schedule.-
Tanja Käser. EPFL (Lausanne, Switzerland).
[Recorded Video] -
Simon Woodhead. Eedi (London, UK).
[Recorded Video; Slides] -
José Miguel Hernández Lobato. University of Cambridge (Cambridge, UK).
[Recorded Video; Slides] -
Min Chi. North Carolina State University (Raleigh, USA).
[Recorded Video] -
Emma Brunskill. Stanford University (Stanford, USA).
[Recorded Video] -
Joe Austerweil. University of Wisconsin-Madison (Madison, USA).
[Recorded Video; Slides] -
Shayan Doroudi. University of California Irvine (Irvine, USA).
[Recorded Video]
Spotlight Presentations
The workshop will have ten short spotlight presentations. These spotlights correspond to the accepted papers and additional invited presentations. You can find more details on the schedule.-
"Statistical Consequences of Dueling Bandits"; Nayan Saxena, Pan Chen, Emmy Liu.
[Recorded Video] -
"Capturing Student-Robot Interactions for a Data-Driven Educational Dialogue RL Environment"; Tristan Maidment, Mingzhi Yu, Erin Walker, Adriana Kovashka, Diane Litman, Timothy Nokes-Malach.
[Recorded Video] -
"Towards Transferrable Personalized Student Models in Educational Games"; Samuel Spaulding, Jocelyn Shen, Hae Won Park, Cynthia Breazeal.
[Recorded Video] -
"Extending Adaptive Spacing Heuristics to Multi-Skill Items"; Benoit Choffin, Fabrice Popineau, Yolaine Bourda.
[Recorded Video] -
"Getting Too Personal(ized): The Importance of Feature Choice in Online Adaptive Algorithms"; Zhaobin Li, Luna Yee, Nathaniel Sauerberg, Irene Sakson, Joseph Jay Williams, Anna Rafferty.
[Recorded Video] -
"Approximately Optimal Teaching of Approximately Optimal Learners"; Jacob Whitehill, Javier Movellan.
[Recorded Video] -
"Learning Expert Models for Educationally Relevant Tasks using Reinforcement Learning"; Christopher Maclellan, Adit Gupta.
[Recorded Video] -
"Deep Reinforcement Learning to Simulate, Train, and Evaluate Instructional Sequencing Policies"; Jithendaraa Subramanian, Jack Mostow.
[Recorded Video] -
"Adaptively Scaffolding Cognitive Engagement with Batch Constrained Deep Q-Networks"; Fahmid Morshed Fahid, Jonathan Rowe, Randall Spain, Benjamin Goldberg, Robert Pokorny, James Lester.
[Recorded Video] -
"Integrating Reinforcement Learning into the ASSISTments Platform"; Ethan Prihar.
[Recorded Video]
Topics of Interest
Topics of interests in the workshop include (but are not limited to) the following:
Leveraging recent advances in RL methods for ED problem setings
- Survey papers summarizing recent advances in RL with applicability to ED.
- Developing toolkits, datasets, and challenges for applying RL methods to ED.
- Using RL for online evaluation and A/B testing of different intervention strategies in ED.
- Novel applications of RL for ED problem settings.
- Using pedagogical theories to narrow the policy space of RL methods.
- Using RL methodology as a computational model of students in open-ended domains.
- Developing novel offline RL methods that can efficiently leverage historical student data.
- Combining statistical power of RL with symbolic reasoning to ensure the robustness for ED.
Call for Papers
We solicit submissions of two types:- Research track papers reporting the results of ongoing or new research, which have not been published before. In particular, we encourage papers covering late-breaking results and work-in-progress research. Submissions should follow the EDM'21 format and are encouraged to be up to four pages, excluding references and appendices. Papers submitted for review do not need to be anonymized. There will be no official proceedings, but the accepted papers will be made available on the workshop website. Accepted papers will be either presented as a talk or poster.
- Encore track papers that have been recently published, or accepted for publication in a conference or journal. For this track, authors only need to submit the Title and Abstract of their paper to the submission site, and no PDF needs to be uploaded. At the end of the Abstract, authors should clearly state the venue where the paper was previously published and provide a URL link to access the PDF of the paper online. Accepted papers will be either presented as a talk or poster. This is a unique opportunity for the researchers to further broaden the dissemination and impact of their important work.
Please submit papers at https://easychair.org/conferences/?conf=rl4ededm21.
Organizers
- Neil T. Heffernan. Worcester Polytechnic Institute (Worcester, USA).
- Goran Radanovic. Max Planck Institute for Software Systems (Saarbrucken, Germany).
- Anna N. Rafferty. Carleton College (Northfield, USA).
- Adish Singla. Max Planck Institute for Software Systems (Saarbrucken, Germany).