Procedural Generation of First Person Shooter Maps using Map-Elites
Procedural Generation of First Person Shooter Maps using Map-Elites
使用 Map-Elites 算法程序化生成第一人称射击游戏地图
Abstract: We investigate the application of MAP-Elites (a well-known quality diversity algorithm) to design levels for First-Person Shooter (FPS) games. We consider two well-known map representations (All-Black and Grid-Graph) and introduce two novel representations (Point-Line and Spatial-Layout) that improve the characterization of FPS maps.
摘要: 我们研究了 MAP-Elites(一种著名的质量多样性算法)在设计第一人称射击(FPS)游戏关卡中的应用。我们考察了两种广为人知的地图表示方法(All-Black 和 Grid-Graph),并引入了两种全新的表示方法(Point-Line 和 Spatial-Layout),这些方法改进了对 FPS 地图特征的描述。
We define a series of metrics to describe maps’ topological properties (which solely depend on maps’ layout), and emergent properties (which must be evaluated through actual gameplay). We perform an in-depth analysis to identify the most suitable features to guide MAP-Elites illumination process.
我们定义了一系列指标来描述地图的拓扑属性(仅取决于地图布局)以及涌现属性(必须通过实际游戏过程进行评估)。我们进行了深入分析,以确定最适合引导 MAP-Elites 启发式搜索(illumination process)的特征。
We apply MAP-Elites with Sliding Boundaries (MESB) to evolve populations of FPS maps. Our results show that the new representations can generate maps with higher diversity and quality than the representations previously used for evolving FPS maps.
我们应用了带有滑动边界的 MAP-Elites (MESB) 来演化 FPS 地图种群。研究结果表明,与以往用于演化 FPS 地图的表示方法相比,这些新方法能够生成具有更高多样性和质量的地图。
Paper Details:
- Authors: Simone de Donato, Pier Luca Lanzi, Daniele Loiacono
- Subject: Artificial Intelligence (cs.AI)
- Date: 28 May 2026
- DOI: 10.48550/arXiv.2605.30570
论文详情:
- 作者: Simone de Donato, Pier Luca Lanzi, Daniele Loiacono
- 学科: 人工智能 (cs.AI)
- 日期: 2026 年 5 月 28 日
- DOI: 10.48550/arXiv.2605.30570