DOOM Level Generation using Generative Adversarial Networks
This addresses level generation for first-person shooter games, but it is incremental as it applies existing GAN methods to a new domain.
The researchers tackled the problem of generating DOOM video game levels by applying Generative Adversarial Networks (GANs) to learn from human-designed content, and found that GANs can capture the intrinsic structure of levels, showing promise for level generation in first-person shooter games.
We applied Generative Adversarial Networks (GANs) to learn a model of DOOM levels from human-designed content. Initially, we analysed the levels and extracted several topological features. Then, for each level, we extracted a set of images identifying the occupied area, the height map, the walls, and the position of game objects. We trained two GANs: one using plain level images, one using both the images and some of the features extracted during the preliminary analysis. We used the two networks to generate new levels and compared the results to assess whether the network trained using also the topological features could generate levels more similar to human-designed ones. Our results show that GANs can capture intrinsic structure of DOOM levels and appears to be a promising approach to level generation in first person shooter games.