Abstract
Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria necessary to present it to end-users and be functional, e.g. the generated levels could be unsolvable or incoherent. In this paper we study this problem from a geometric perspective, and provide a method for reliable interpolation and random walks in the latent spaces of Categorical VAEs based on Riemannian geometry. We test our method with “Super Mario Bros” and “The Legend of Zelda” levels, and against simpler baselines inspired by current practice. Results show that the geometry we propose is better able to interpolate and sample, reliably staying closer to parts of the latent space that decode to playable content.
Originalsprog | Engelsk |
---|---|
Tidsskrift | Proceedings of the 2022 IEEE Conference on Games (CoG) |
ISSN | 2325-4289 |
Status | Udgivet - 2022 |
Emneord
- Deep Generative Models
- Content Validity
- Categorical VAEs
- Riemannian Geometry
- Procedural Content Generation