Matthew Siper, Sam Earle, Zehua Jiang, Ahmed Khalifa, Julian Togelius
TL;DR这篇论文介绍了一种名为 PoD 的自监督学习方法,用于学习迭代生成器,特别适用于由分类数据组成的功能性工件,扩展后可以允许设计师控制生成物品的方方面面。
Abstract
Path of Destruction (PoD) is a self-supervised method for learning iterative
generators. The core idea is to produce a training set by destroying a set of
artifacts, and for each destructive step create a training instance based on
the corresponding repair action. A generator trained o