Addressing the Fundamental Tension of PCGML with Discriminative Learning
This addresses the efficiency problem for artists and designers in procedural content generation, offering a more interactive and controlled approach, though it is incremental as it builds on existing methods.
The paper tackles the tension in PCGML where detailed training examples reduce the return on investment, by proposing discriminative models trained on positive and negative examples to capture design validity. They demonstrate this through a modified WaveFunctionCollapse, showing how artists can critique outputs to define a space of valid designs.
Procedural content generation via machine learning (PCGML) is typically framed as the task of fitting a generative model to full-scale examples of a desired content distribution. This approach presents a fundamental tension: the more design effort expended to produce detailed training examples for shaping a generator, the lower the return on investment from applying PCGML in the first place. In response, we propose the use of discriminative models (which capture the validity of a design rather the distribution of the content) trained on positive and negative examples. Through a modest modification of WaveFunctionCollapse, a commercially-adopted PCG approach that we characterize as using elementary machine learning, we demonstrate a new mode of control for learning-based generators. We demonstrate how an artist might craft a focused set of additional positive and negative examples by critique of the generator's previous outputs. This interaction mode bridges PCGML with mixed-initiative design assistance tools by working with a machine to define a space of valid designs rather than just one new design.