Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)
This work addresses personalized therapy for arachnophobia patients by automating content adaptation, though it is incremental as it builds on existing EDPCG approaches and uses virtual humans due to pandemic constraints.
The paper tackles the problem of automatically adapting therapeutic content for arachnophobia exposure therapy by using experience-driven procedural content generation via reinforcement learning (EDPCGRL) to generate virtual spiders based on physiological measures, achieving faster adaptation with high accuracy compared to existing search-based methods.
Personalized therapy, in which a therapeutic practice is adapted to an individual patient, leads to better health outcomes. Typically, this is accomplished by relying on a therapist's training and intuition along with feedback from a patient. While there exist approaches to automatically adapt therapeutic content to a patient, they rely on hand-authored, pre-defined rules, which may not generalize to all individuals. In this paper, we propose an approach to automatically adapt therapeutic content to patients based on physiological measures. We implement our approach in the context of arachnophobia exposure therapy, and rely on experience-driven procedural content generation via reinforcement learning (EDPCGRL) to generate virtual spiders to match an individual patient. In this initial implementation, and due to the ongoing pandemic, we make use of virtual or artificial humans implemented based on prior arachnophobia psychology research. Our EDPCGRL method is able to more quickly adapt to these virtual humans with high accuracy in comparison to existing, search-based EDPCG approaches.