Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoders
This work addresses the challenge of combinational creativity in game level generation for PCGML practitioners, though it appears incremental as it builds on prior methods.
The paper tackles the problem of generating and blending level structures across multiple domains in procedural content generation via machine learning (PCGML), by extending example-driven Binary Space Partitioning and incorporating Variational Autoencoders to recombine patterns and generate unseen structures, resulting in the ability to blend across 7 domains while retaining structural components and generate levels that either reproduce target domain features or have vastly different properties.
Procedural content generation via machine learning (PCGML) has demonstrated its usefulness as a content and game creation approach, and has been shown to be able to support human creativity. An important facet of creativity is combinational creativity or the recombination, adaptation, and reuse of ideas and concepts between and across domains. In this paper, we present a PCGML approach for level generation that is able to recombine, adapt, and reuse structural patterns from several domains to approximate unseen domains. We extend prior work involving example-driven Binary Space Partitioning for recombining and reusing patterns in multiple domains, and incorporate Variational Autoencoders (VAEs) for generating unseen structures. We evaluate our approach by blending across $7$ domains and subsets of those domains. We show that our approach is able to blend domains together while retaining structural components. Additionally, by using different groups of training domains our approach is able to generate both 1) levels that reproduce and capture features of a target domain, and 2) levels that have vastly different properties from the input domain.