Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/82048| Title: | Mixed-initiative level design with RL brush |
| Authors: | Delarosa, Omar Dong, Hang Ruan, Mindy Khalifa, Ahmed |
| Keywords: | Computer games -- Design Level design (Computer science) Artificial intelligence Machine learning Reinforcement learning |
| Issue Date: | 2021 |
| Publisher: | Springer |
| Citation: | Delarosa, O., Dong, H., Ruan, M., & Khalifa, A. (2021). Mixed-initiative level design with RL brush. EvoMUSART 2021: Artificial Intelligence in Music, Sound, Art and Design. 412-426. |
| Abstract: | 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. |
| URI: | https://www.um.edu.mt/library/oar/handle/123456789/82048 |
| Appears in Collections: | Scholarly Works - InsDG |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Mixed-initiative_level_design_with_RL_brush_2021.pdf Restricted Access | 1.78 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.