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.
Cite
@article{arxiv.2008.02778,
title = {Mixed-Initiative Level Design with RL Brush},
author = {Omar Delarosa and Hang Dong and Mindy Ruan and Ahmed Khalifa and Julian Togelius},
journal= {arXiv preprint arXiv:2008.02778},
year = {2021}
}