Controllable Path of Destruction
This work addresses the need for more user control in generative models for functional artifacts like game levels, but it is incremental as it builds on an existing method.
The paper tackles the problem of adding designer control to the Path of Destruction method for generating artifacts, and the result is a controllable version that allows conditional inputs to influence repair trajectories, tested in 2D dungeons and 3D Lego cars.
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 on this dataset can then generate new artifacts by repairing from arbitrary states. The PoD method is very data-efficient in terms of original training examples and well-suited to functional artifacts composed of categorical data, such as game levels and discrete 3D structures. In this paper, we extend the Path of Destruction method to allow designer control over aspects of the generated artifacts. Controllability is introduced by adding conditional inputs to the state-action pairs that make up the repair trajectories. We test the controllable PoD method in a 2D dungeon setting, as well as in the domain of small 3D Lego cars.