Deep Learning for Procedural Content Generation

However, the computational creativity community combined with LVE can allow users to breed their own has identified that in order to get a full picture game levels, such as Zelda and Mario [104]. Based on of the generator (or creative program) the process by [36, 140], a mixed-initiative tile-based level design tool which the output content is created should be evaluated was implemented by Schrum et al. [103], which allows as well. Colton [11], Jordanous [56], Pease and human to interact with the evolution and exploration Colton [86] each propose frameworks and methodologies within latent level-design space (interface illustrated in for evaluating the creativity of the process of a generator. Figure 1), and to play the generated levels in real-time. Smith and Whitehead [116] (later expanded on by Summerville [125]) proposed methods for holistically EC methods can also collaborate with human to evaluating a content generation approach, by evaluating generate and evaluate or repair game content. Liapis large swaths of generated content to get a broader et al. [71] presented Sentient World tool which allows understanding of the generative space of a content generator interactions with human designers and generates game and its biases within that generative space.