Coevolution of AI and level generation for Super Mario game
| Thesis title in Czech: | Koevoluce AI a generování levelů do hry Super Mario |
|---|---|
| Thesis title in English: | Coevolution of AI and level generation for Super Mario game |
| Key words: | koevoluce, umělá inteligence, procedurální generování obsahu, Super Mario |
| English key words: | coevolution, artificial intelligence, procedural content generation, Super Mario |
| Academic year of topic announcement: | 2019/2020 |
| Thesis type: | diploma thesis |
| Thesis language: | angličtina |
| Department: | Department of Software and Computer Science Education (32-KSVI) |
| Supervisor: | Mgr. Vojtěch Černý |
| Author: | hidden - assigned and confirmed by the Study Dept. |
| Date of registration: | 24.02.2020 |
| Date of assignment: | 25.02.2020 |
| Confirmed by Study dept. on: | 27.02.2020 |
| Date and time of defence: | 16.09.2020 09:00 |
| Date of electronic submission: | 29.07.2020 |
| Date of submission of printed version: | 30.07.2020 |
| Date of proceeded defence: | 16.09.2020 |
| Opponents: | Mgr. Martin Pilát, Ph.D. |
| Advisors: | Mgr. Jakub Gemrot, Ph.D. |
| Guidelines |
| The goal of this thesis is to use coevolution to create a player controlled by artificial intelligence (AI) and procedural level generators for a classic platformer game Super Mario. An open-source clone of this game will be used. AI players will be used to evaluate the outputs of the level generators, and vice versa, procedural generators will be evaluated by the AI players. The thesis will include a comparison of achieved results with related works in areas of playing Super Mario by AI and generating levels for it. |
| References |
| Togelius, J., Karakovskiy, S., Koutník, J., & Schmidhuber, J. (2009, September). Super mario evolution. In 2009 IEEE symposium on computational intelligence and games (pp. 156-161). IEEE.
Shaker, N., Togelius, J., Yannakakis, G. N., Weber, B., Shimizu, T., Hashiyama, T., ... & Smith, G. (2011). The 2010 Mario AI championship: Level generation track. IEEE Transactions on Computational Intelligence and AI in Games, 3(4), 332-347. Dahlskog, S., & Togelius, J. (2013). Patterns as objectives for level generation.(2013). Černý, V. (2018). Procedural Generation of Endless Runner Type of Video Games. Stanley, K. O., & Miikkulainen, R. (2002). Evolving neural networks through augmenting topologies. Evolutionary computation, 10(2), 99-127. |