Building a Reinforcement Learning Environment from Limited Data to Optimize Teachable Robot Interventions

Intelligent social agents provide an additional source of personalized support for students in an educational setting. Current educational theories suggest that working collaboratively in groups can positively impact performance and student engagement. Reinforcement learning (RL) offers an opportunity for adapting the interactions between the social agent and the students to better support collaboration and learning. However, using RL in education with social agents typically involves training using real students. In the current work, we train an RL agent in a high-quality simulated environment to learn how to improve students' collaboration. Data was collected during a pilot study with dyads of students who worked together to tutor an intelligent teachable robot. We explore the process of building an environment from the data, training a policy, and the impact of the policy on different students, compared to various baselines.