paper-with-me

홈 › Papers

Learning Local Constraints for Reinforcement-Learned Content Generators

2026-05-13 · Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis, Ahmed Khalifa arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.13570

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Controllable 3D Level Generators

2022-06-27 · Zehua Jiang, Sam Earle, Michael Cerny Green, Julian Togelius

Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraints, using computable, user-defined measur…

Minecraft

Video Game Level Design as a Multi-Agent Reinforcement Learning Problem

2025-10-06 · Sam Earle, Zehua Jiang, Eugene Vinitsky, Julian Togelius arxiv

Procedural Content Generation via Reinforcement Learning (PCGRL) offers a method for training controllable level designer agents without the need for human datasets, using metrics that serve as proxies for level quality …

Multi-agent Reinforcement Learning

MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned from Image Pairs

2023-03-06 · Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan

Video generation has achieved rapid progress benefiting from high-quality renderings provided by powerful image generators. We regard the video synthesis task as generating a sequence of images sharing the same contents …

Motion GenerationUnconditional Video GenerationVideo Generation

Learning Controllable Content Generators

2021-05-06 · Sam Earle, Maria Edwards, Ahmed Khalifa, Philip Bontrager 외

It has recently been shown that reinforcement learning can be used to train generators capable of producing high-quality game levels, with quality defined in terms of some user-specified heuristic. To ensure that these g…

Procedural Content Metageneration via Program Search and Continual Abstraction Discovery

2026-08-18 · Matthew Siper, Ahmed Khalifa, Julian Togelius arxiv

Large language models can generate executable programs, which makes it possible to search directly over procedural content generators rather than individual levels. We study this approach in Sokoban, Zelda, Dangerous Dav…