# Mixed-Initiative Level Design with RL Brush

arXiv: https://arxiv.org/abs/2008.02778 · HTML: https://mlsanity.com/paper/2008.02778/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 13 of 13)

- [Learning Controllable Content Generators](https://mlsanity.com/paper/2105.02993/) (2021)
- [Illuminating Diverse Neural Cellular Automata for Level Generation](https://mlsanity.com/paper/2109.05489/) (2021)
- [Learning Controllable 3D Level Generators](https://mlsanity.com/paper/2206.13623/) (2022)
- [Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset](https://mlsanity.com/paper/2202.10184/) (2022)
- [Mutation Models: Learning to Generate Levels by Imitating Evolution](https://mlsanity.com/paper/2206.05497/) (2022)
- [Generative Personas That Behave and Experience Like Humans](https://mlsanity.com/paper/2209.00459/) (2022)
- [PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators](https://mlsanity.com/paper/2408.12525/) (2024)
- [Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI](https://mlsanity.com/paper/2211.02759/) (2022)
- [Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes](https://mlsanity.com/paper/2209.15052/) (2022)
- [Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation](https://mlsanity.com/paper/2508.09860/) (2025)
- [Toward Co-creative Dungeon Generation via Transfer Learning](https://mlsanity.com/paper/2107.12533/) (2021)
- [Lode Enhancer: Level Co-creation Through Scaling](https://mlsanity.com/paper/2308.01543/) (2023)
- [Video Game Level Design as a Multi-Agent Reinforcement Learning Problem](https://mlsanity.com/paper/2510.04862/) (2025)

## Abstract (arXiv)

This paper introduces RL Brush, a level-editing tool for tile-based games designed for mixed-initiative co-creation. The tool uses reinforcement-learning-based models to augment manual human level-design through the addition of AI-generated suggestions. Here, we apply RL Brush to designing levels for the classic puzzle game Sokoban. We put the tool online and tested it in 39 different sessions. The results show that users using the AI suggestions stay around longer and their created levels on average are more playable and more complex than without.