We propose a new procedural content generation method which learns iterative level generators from a dataset of existing levels. The Path of Destruction method, as we call it, views level generation as repair; levels are created by iteratively repairing from a random starting level. The first step is to generate an artificial dataset from the original set of levels by introducing many different sequences of mutations to existing levels. In the generated dataset, features are observations of destroyed levels and targets are the specific actions that repair the mutated tile in the middle of the observations. Using this dataset, a convolutional network is trained to map from observations to their respective appropriate repair actions. The trained network is then used to iteratively produce levels from random starting maps. We demonstrate this method by applying it to generate unique and playable tile-based levels for several 2D games (Zelda, Danger Dave, and Sokoban) and vary key hyperparameters.
翻译:我们建议一种新的程序内容生成方法,从现有水平的数据集中学习迭代级生成器。“销毁路径”方法,我们称之为“销毁路径”方法,将水平生成视为修理;水平是通过随机初始水平的迭接修复产生的。第一步是将许多不同的变异序列引入现有水平,从原始水平生成一个人工数据集。在生成的数据集中,观测破坏的水平和目标是修复观察中间变异瓦的具体行动。使用这一数据集,对一个革命网络进行培训,从观测到相应的适当修复行动。然后,培训过的网络用于从随机启动的地图中迭接生成水平。我们通过应用这种方法为多个2D游戏(Zelda、Degreen Dave和Sokoban)生成独特和可播放的瓦基水平,并使用不同的关键超参数。