Learning Local Constraints for Reinforcement-Learned Content Generators

• URL: http://arxiv.org/abs/2605.13570v1
• Date: Wed, 13 May 2026 14:07:10 GMT
• Title: Learning Local Constraints for Reinforcement-Learned Content Generators
• Abstract summary: Constraint-based game content generators learn local constraints from existing content, such as Wave Collapse Function (WFC)<n> reinforcement-learning generators can guarantee global properties, but the results can be visually dissatisfying.<n>In this paper, we explore ways to combine these methods. Specifically, we constrain the action space of a PCGRL generator with constraints learned by WFC.
• Score: 5.920650312783903
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Constraint-based game content generators that learn local constraints from existing content, such as Wave Function Collapse (WFC), can generate visually satisfying game levels but face challenges in guaranteeing global properties, such as playability. On the other hand, reinforcement-learning trained generators can guarantee global properties -- because such properties can easily be included in reward functions -- but the results can be visually dissatisfying. In this paper, we explore ways to combine these methods. Specifically, we constrain the action space of a PCGRL generator with constraints learned by WFC, effectively allowing the PCGRL generator to achieve global properties while forced to adhere to local constraints. To better analyze how this hybrid content generation method operates, we vary the number and type of inputs, and we test whether to randomly collapse the starting state and exclude rare patterns. While the method is sensitive to hyperparameter tuning, the best of our trained generators produce visually satisfying and playable puzzle-platform game levels -- such as Lode Runner levels -- with desired global properties.

Related papers

• Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan [19.27715432069165]
  We introduce a next-scale generator (NSG) that progressively expands a recommendation list from user interests in a coarse-to-fine manner.<n>NSGR has been successfully deployed on the Meituan food delivery platform.
  arXiv  Detail & Related papers  (2026-04-07T01:35:20Z)
• UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction [83.48950950780554]
  Building extraction from remote sensing images is a challenging task due to the complex structure variations of buildings.<n>Existing methods employ convolutional or self-attention blocks to capture the multi-scale features in the segmentation models.<n>We present an Uncertainty-Aggregated Global-Local Fusion Network (UAGLNet) to exploit high-quality global-local visual semantics.
  arXiv  Detail & Related papers  (2025-12-15T02:59:16Z)
• Level Generation with Constrained Expressive Range [3.2228025627337864]
  Expressive range analysis is a visualization-based technique used to evaluate the performance of generative models.<n>In this work, we use the expressive range of a generator as the conceptual space of possible creations.<n>To do so, we use a constraint-based generator that systematically traverses and generates levels in this space.
  arXiv  Detail & Related papers  (2025-04-04T20:55:30Z)
• Generating Compositional Scenes via Text-to-image RGBA Instance Generation [82.63805151691024]
  Text-to-image diffusion generative models can generate high quality images at the cost of tedious prompt engineering. We propose a novel multi-stage generation paradigm that is designed for fine-grained control, flexibility and interactivity. Our experiments show that our RGBA diffusion model is capable of generating diverse and high quality instances with precise control over object attributes.
  arXiv  Detail & Related papers  (2024-11-16T23:44:14Z)
• A Feature Generator for Few-Shot Learning [2.4500728886415137]
  Few-shot learning aims to enable models to recognize novel objects or classes with limited labelled data. We introduce a feature generator that creates visual features from class-level textual descriptions. Our results show a significant improvement in accuracy over baseline methods.
  arXiv  Detail & Related papers  (2024-09-21T13:31:12Z)
• GraCo: Granularity-Controllable Interactive Segmentation [52.9695642626127]
  Granularity-Controllable Interactive (GraCo) is a novel approach that allows precise control of prediction granularity by introducing additional parameters to input. GraCo exploits the semantic property of the pre-trained IS model to automatically generate abundant mask-granularity pairs. Experiments on intricate scenarios at object and part levels demonstrate that our GraCo has significant advantages over previous methods.
  arXiv  Detail & Related papers  (2024-05-01T15:50:16Z)
• Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation [54.419401869108846]
  We propose a single-stage WeaklySupervised Semantic (WSSS) model with only the image-level class label supervisions. A flexible context aggregation module is proposed to capture the global object context in different granular spaces. A semantically consistent feature fusion module is proposed in a bottom-up parameter-learnable fashion to aggregate the fine-grained local contents.
  arXiv  Detail & Related papers  (2023-04-18T15:29:23Z)
• Controllable and Compositional Generation with Latent-Space Energy-Based Models [60.87740144816278]
  Controllable generation is one of the key requirements for successful adoption of deep generative models in real-world applications. In this work, we use energy-based models (EBMs) to handle compositional generation over a set of attributes. By composing energy functions with logical operators, this work is the first to achieve such compositionality in generating photo-realistic images of resolution 1024x1024.
  arXiv  Detail & Related papers  (2021-10-21T03:31:45Z)
• Learning Controllable Content Generators [5.5805433423452895]
  We train generators capable of producing controllably diverse output, by making them "goal-aware" We show that the resulting level generators are capable of exploring the space of possible levels in a targeted, controllable manner.
  arXiv  Detail & Related papers  (2021-05-06T22:15:51Z)
• Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution [25.262831218008202]
  We develop a deep-generative-model-based level generation for the game domain of Angry Birds. Experiments show that the proposed level generator drastically improves the stability and diversity of generated levels.
  arXiv  Detail & Related papers  (2021-04-13T11:23:39Z)
• Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments [137.86426963572214]
  Inverse Reinforcement Learning can extrapolate reward functions from expert demonstrations. We show that our approach, DE-AIRL, is demonstration-efficient and still able to extrapolate reward functions which generalize to the fully procedural domain.
  arXiv  Detail & Related papers  (2020-12-04T11:18:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.