Procedural content generation via machine learning (PCGML) has recently gained research attention due to its ability to generate new game content with minimal user input. However, thus far those without machine learning expertise have been largely unable to use PCGML to generate content to fit their needs. This paper proposes the use of images as the input for a PCGML process to generate game levels. Intuitively, a user can submit an image, with the system returning the closest valid Super Mario Bros. game level. Our results indicate that at least for domains like Super Mario Bros. we can recreate a target level with high fidelity.

The combination of tree search and neural networks has achieved super-human performance in challenging domains. We are interested in transferring to humans the knowledge these learning systems generate. We hypothesize the process in which neural-guided tree search algorithms learn how to solve a set of problems can be used to generate curricula for helping human learners. In this paper we show how the Bootstrap learning system can be modified to learn curricula for humans in a puzzle domain. We evaluate our system in two curriculum learning settings. First, given a small set of problem instances, our system orders the instances to ease the learning process of human learners. Second, given a large set of problem instances, our system returns a small ordered subset of the initial set that can be presented to human learners. We evaluate our curricula with a user study where participants learn how to solve a class of puzzles from the game `The Witness.' The user-study results suggest one of the curricula our system generates compares favorably with simple baselines and is competitive with the curriculum from the original `The Witness' game in terms of user retention and effort.