# Addressing the Fundamental Tension of PCGML with Discriminative Learning

arXiv: https://arxiv.org/abs/1809.04432 · HTML: https://mlsanity.com/paper/1809.04432/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [Level Generation Through Large Language Models](https://mlsanity.com/paper/2302.05817/) (2023)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators](https://mlsanity.com/paper/2408.12525/) (2024)
- [10 Years of the PCG workshop: Past and Future Trends](https://mlsanity.com/paper/2104.11037/) (2021)
- [Analysis of Robustness of a Large Game Corpus](https://mlsanity.com/paper/2504.03940/) (2025)
- [Level Assembly as a Markov Decision Process](https://mlsanity.com/paper/2304.13922/) (2023)
- [RuleSmith: Multi-Agent LLMs for Automated Game Balancing](https://mlsanity.com/paper/2602.06232/) (2026)
- [Learning Local Constraints for Reinforcement-Learned Content Generators](https://mlsanity.com/paper/2605.13570/) (2026)

## Abstract (arXiv)

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.