Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reinforcement Learning-Enhanced Procedural Generation for Dynamic Narrative-Driven AR Experiences

Aniruddha Srinivas Joshi

TL;DR

This work tackles the limitation of static procedural generation in narrative-driven AR by fusing reinforcement learning with Wave Function Collapse to create biome-aware, adaptive maps. The approach introduces environment-specific constraints and a PPO-based policy to dynamically adjust tile weights during map generation, enabling coherent paths and responsive layouts in real time. Experiments show the method outperforms baseline PCG techniques in map quality and immersion, albeit with higher computational costs, and user studies confirm its narrative-compatibility and usability. The framework holds promise for education, training, and immersive XR experiences where dynamic, context-aware environments enhance engagement and storytelling.

Abstract

Procedural Content Generation (PCG) is widely used to create scalable and diverse environments in games. However, existing methods, such as the Wave Function Collapse (WFC) algorithm, are often limited to static scenarios and lack the adaptability required for dynamic, narrative-driven applications, particularly in augmented reality (AR) games. This paper presents a reinforcement learning-enhanced WFC framework designed for mobile AR environments. By integrating environment-specific rules and dynamic tile weight adjustments informed by reinforcement learning (RL), the proposed method generates maps that are both contextually coherent and responsive to gameplay needs. Comparative evaluations and user studies demonstrate that the framework achieves superior map quality and delivers immersive experiences, making it well-suited for narrative-driven AR games. Additionally, the method holds promise for broader applications in education, simulation training, and immersive extended reality (XR) experiences, where dynamic and adaptive environments are critical.

Reinforcement Learning-Enhanced Procedural Generation for Dynamic Narrative-Driven AR Experiences

TL;DR

This work tackles the limitation of static procedural generation in narrative-driven AR by fusing reinforcement learning with Wave Function Collapse to create biome-aware, adaptive maps. The approach introduces environment-specific constraints and a PPO-based policy to dynamically adjust tile weights during map generation, enabling coherent paths and responsive layouts in real time. Experiments show the method outperforms baseline PCG techniques in map quality and immersion, albeit with higher computational costs, and user studies confirm its narrative-compatibility and usability. The framework holds promise for education, training, and immersive XR experiences where dynamic, context-aware environments enhance engagement and storytelling.

Abstract

Procedural Content Generation (PCG) is widely used to create scalable and diverse environments in games. However, existing methods, such as the Wave Function Collapse (WFC) algorithm, are often limited to static scenarios and lack the adaptability required for dynamic, narrative-driven applications, particularly in augmented reality (AR) games. This paper presents a reinforcement learning-enhanced WFC framework designed for mobile AR environments. By integrating environment-specific rules and dynamic tile weight adjustments informed by reinforcement learning (RL), the proposed method generates maps that are both contextually coherent and responsive to gameplay needs. Comparative evaluations and user studies demonstrate that the framework achieves superior map quality and delivers immersive experiences, making it well-suited for narrative-driven AR games. Additionally, the method holds promise for broader applications in education, simulation training, and immersive extended reality (XR) experiences, where dynamic and adaptive environments are critical.
Paper Structure (25 sections, 4 equations, 4 figures, 6 tables)

This paper contains 25 sections, 4 equations, 4 figures, 6 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORKS
  3. Procedural Generation in Games
  4. Machine learning in Procedural Generation
  5. Procedural Generation in Augmented Reality
  6. AR/VR/XR in Narrative Games
  7. METHOD
  8. Proposed Procedural Generation Method
  9. Tile Weight Calculation and Selection
  10. Path Layout Strategies
  11. Continuous Path Layouts:
  12. Sparse Path Layouts:
  13. Reinforcement Learning for Procedural Map Generation
  14. Agent Training
  15. Policy Deployment
  16. ...and 10 more sections

Figures (4)

  • Figure 1: Real-time screen capture of 10×10 grids for City, Desert, and Forest biomes.
  • Figure 2: High-level diagram of the proposed method.
  • Figure 3: Real-time screen captures showcasing dynamic controls offered by the proposed method.
  • Figure 4: Close up real-time screen captures of environments generated by the proposed method.