Spiders Based on Anxiety: How Reinforcement Learning Can Deliver Desired User Experience in Virtual Reality Personalized Arachnophobia Treatment
This addresses the time-consuming and expertise-intensive process of manually selecting spiders in VRET for arachnophobia patients, though it is incremental as it builds on existing automated methods.
The paper tackles the problem of automating spider generation for personalized virtual reality exposure therapy (VRET) for arachnophobia, presenting a framework that uses procedural content generation and reinforcement learning to adapt spiders to elicit desired anxiety responses, and demonstrates superior performance compared to a rules-based method.
The need to generate a spider to provoke a desired anxiety response arises in the context of personalized virtual reality exposure therapy (VRET), a treatment approach for arachnophobia. This treatment involves patients observing virtual spiders in order to become desensitized and decrease their phobia, which requires that the spiders elicit specific anxiety responses. However, VRET approaches tend to require therapists to hand-select the appropriate spider for each patient, which is a time-consuming process and takes significant technical knowledge and patient insight. While automated methods exist, they tend to employ rules-based approaches with minimal ability to adapt to specific users. To address these challenges, we present a framework for VRET utilizing procedural content generation (PCG) and reinforcement learning (RL), which automatically adapts a spider to elicit a desired anxiety response. We demonstrate the superior performance of this system compared to a more common rules-based VRET method.