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.
翻译:本文介绍RL Brush, 这是设计用于混合活动共创的基于瓷砖的游戏的级别编辑工具。 该工具使用强化学习模型, 通过添加 AI 生成的建议来增强人工设计。 在此, 我们应用 RL Brush 来设计经典拼图游戏 Sokoban 的级别 。 我们将该工具放在网上, 并在39场不同的会议上测试它 。 结果显示, 使用 AI 建议的用户在时间上停留更长, 他们的创建水平平均比没有工具更方便玩, 也更复杂 。