Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.13570 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918499705683968 |
|---|---|
| author | Bhaumik, Debosmita Togelius, Julian Yannakakis, Georgios N. Khalifa, Ahmed |
| author_facet | Bhaumik, Debosmita Togelius, Julian Yannakakis, Georgios N. Khalifa, Ahmed |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13570 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Local Constraints for Reinforcement-Learned Content Generators Bhaumik, Debosmita Togelius, Julian Yannakakis, Georgios N. Khalifa, Ahmed Artificial Intelligence Machine Learning 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. |
| title | Learning Local Constraints for Reinforcement-Learned Content Generators |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.13570 |