Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration

Valerant：一种通过动作条件世界模型探索实现自动导航游戏地图生成的框架

World Action Models (WAMs) couple predictive world modeling with action generation, allowing anticipated future states to guide agent behavior. Although WAMs are rapidly advancing embodied AI, general-purpose counterparts remain largely unexplored in games. 世界动作模型（WAMs）将预测性世界建模与动作生成相结合，使预期的未来状态能够引导智能体的行为。尽管 WAMs 正在迅速推动具身智能的发展，但其在游戏领域的通用对应方案仍未得到充分探索。

Existing game-oriented approaches often combine action-conditioned world models with external policies and reward functions to realize WAM-like decision-making, yet they operate mainly in 2D visual observation space and do not instantiate persistent 3D geometry. Extending this paradigm to 3D games introduces a distinct challenge. 现有的游戏导向方法通常将动作条件世界模型与外部策略和奖励函数相结合，以实现类似 WAM 的决策，但它们主要在二维视觉观察空间中运行，无法实例化持久的三维几何结构。将这种范式扩展到三维游戏带来了独特的挑战。

In autonomous driving and robotics, the physical environment exists independently of the model, providing a persistent 3D world in which selected actions can be executed. Games have no such external substrate; the virtual world itself must be instantiated. Most playable games require a persistent and navigable space, while 3D games additionally require explicit geometry that supports movement and interaction. Action-conditioned video rollouts provide visual observations but not this spatial representation. 在自动驾驶和机器人技术中，物理环境独立于模型存在，提供了一个可以执行所选动作的持久三维世界。而游戏没有这种外部基质；虚拟世界本身必须被实例化。大多数可玩游戏需要一个持久且可导航的空间，而三维游戏还需要支持移动和交互的显式几何结构。动作条件视频推演（Video rollouts）虽然能提供视觉观察，却无法提供这种空间表示。

We present \textsc{Valerant}, a training-free framework that transforms a pretrained action-conditioned world model into a WAM for exploring and constructing 3D game maps. By coupling predictive visual rollouts with SLAM-based spatial reconstruction and exploration-driven action selection, \textsc{Valerant} progressively transforms a single image into a persistent 3D game map. This framework extends WAM-based interaction beyond 2D visual simulation and offers a new approach to reducing manual effort in 3D game-map creation. 我们提出了 \textsc{Valerant}，这是一个无需训练的框架，它将预训练的动作条件世界模型转化为用于探索和构建三维游戏地图的 WAM。通过将预测性视觉推演与基于 SLAM 的空间重建以及探索驱动的动作选择相结合，\textsc{Valerant} 能够逐步将单张图像转化为持久的三维游戏地图。该框架将基于 WAM 的交互扩展到了二维视觉模拟之外，并为减少三维游戏地图制作中的人工投入提供了一种新方法。