Spiders Based on Anxiety: How Reinforcement Learning Can Deliver Desired User Experience in Virtual Reality Personalized Arachnophobia Treatment

2024-09-25

arXiv.org

AI Summary

To address the time-consuming manual selection, poor generalizability, and insufficient personalization of virtual spiders in spider-phobia Virtual Reality Exposure Therapy (VRET), this study proposes the first closed-loop adaptive system integrating Proximal Policy Optimization (PPO)-based reinforcement learning with procedural content generation (PCG). The system dynamically generates virtual spiders that elicit target anxiety levels, leveraging real-time physiological and behavioral user feedback, and renders them in VR with millisecond latency for fine-grained personalization. Compared to conventional rule-based approaches, it improves anxiety-response matching accuracy by 37% and increases session-level personalization compliance by 52%, while substantially reducing clinical configuration time. This work overcomes therapist dependence and static rule paradigms, establishing a scalable, data-driven framework for personalized VRET interventions.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Automating spider generation for personalized VR exposure therapy
• Adapting virtual spiders to elicit specific anxiety responses
• Replacing manual therapist selection with reinforcement learning

Innovation

• Reinforcement learning adapts spider for anxiety response
• Procedural content generation creates personalized virtual spiders
• Automated framework replaces therapist hand-selection process