mlsanityData to 14 Oct 2026

Controllable Path of Destruction

arXiv 2305.18553 ↗First posted 29 May 2023cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Path of Destruction (PoD) is a self-supervised method for learning iterative generators. The core idea is to produce a training set by destroying a set of artifacts, and for each destructive step create a training instance based on the corresponding repair action. A generator trained on this dataset can then generate new artifacts by repairing from arbitrary states. The PoD method is very data-efficient in terms of original training examples and well-suited to functional artifacts composed of categorical data, such as game levels and discrete 3D structures. In this paper, we extend the Path of Destruction method to allow designer control over aspects of the generated artifacts. Controllability is introduced by adding conditional inputs to the state-action pairs that make up the repair trajectories. We test the controllable PoD method in a 2D dungeon setting, as well as in the domain of small 3D Lego cars.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

15 of 22 references.

References · 15

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  7. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 137
  8. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  9. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 81
  10. 2020Deep Learning for Procedural Content Generationcited by 73
  11. 2019Increasing Generality in Machine Learning through Procedural Content Generationcited by 59
  12. 2021Learning Controllable Content Generatorscited by 40
3 more
  1. 2019Language Models with Transformerscited by 36
  2. 2019Bootstrapping Conditional GANs for Video Game Level Generationcited by 35
  3. 2022Path of Destruction: Learning an Iterative Level Generator Using a Small Datasetcited by 14

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Measuring Diversity of Game Scenarioscited by 5