Deep Quality Diversity
Open-Ended Evolution for Minecraft Building Generation

The github repository, immersive article, and research paper provided demonstrate how deep quality diversity (DQD) can be used to generate interesting and diverse artefacts such as Minecraft buildings. We present several variations of this approach and highlight their respective strenghts and weaknesses. The provided framework can be modified to generate content for other domains and use-cases.
Deep Quality Diversity (DQD) refers to AI algorithms which utilize deep learning to generate content that is (a) of high quality according to an objective function, and (b) maximizes diversity along one or more measures. The included research paper proposes a procedural content generator which evolves Minecraft buildings according to an open-ended and intrinsic definition of novelty.
To realize this goal we evaluate individuals' novelty in the latent space using a 3D autoencoder, and alternate between phases of exploration and transformation. During exploration the system evolves multiple populations of CPPNs through CPPN-NEAT and constrained novelty search in the latent space (defined by the current autoencoder). We apply a set of repair and constraint functions to ensure candidates adhere to basic structural rules and constraints during evolution. During transformation, we reshape the boundaries of the latent space to identify new interesting areas of the solution space by retraining the autoencoder with novel content. In this study we evaluate five different approaches for training the autoencoder during transformation and its impact on populations' quality and diversity during evolution. Our results show that by retraining the autoencoder we can achieve better open-ended complexity compared to a static model, which is further improved when retraining using larger datasets of individuals with diverse complexities.