Papers related to the Gameplay track:
The following paper describes the Mario AI benchmark:
The following paper describes experiments with evolving neural networks to play Mario as implemented in the 2009 competition software:
And this paper describes 2009 submissions for the GamePlay track and is co-authored by the winner of the competition.
- Julian Togelius, Sergey Karakovskiy, Jan Koutnik and Jürgen Schmidhuber (2009): Super Mario Evolution. Proceedings of the IEEE Symposium on Computational Intelligence and Games.
- Julian Togelius, Sergey Karakovskiy and Robin Baumgarten (2010): The 2009 Mario AI Competition. To be presented at IEEE Congress on Evolutionary Computation (CEC).
Papers related to Level Generation track:
The following papers relate to the Level Generation track, detailing a number of measurements of player experience in Infinite Mario Bros and an approach to evolving new levels based on these measurements:
- N. Shaker, J. Togelius, G. N. Yannakakis, B. Weber, T. Shimizu, T. Hashiyama, N, Soreson, P. Pasquier, P. Mawhorter, G. Takahashi, G. Smith, and R. Baumgarten. The 2010 Mario AI Championship: Level Generation Track, In special Issue of IEEE Transactions on Procedural Content Generation.
- Noor Shaker, Georgios Yannakakis and Julian Togelius (2010): Towards Automatic Personalized Content Generation for Platform Games.To be presented at AIIDE Conference on AI and Interactive Digital Entertainment
The following paper describes the submissions to the 2010 level generation track competition and is co-authored by the competitors of the competition:
- Noor Shaker, Julian Togelius, Georgios N. Yannakakis, Ben Weber, Tomoyuki Shimizu, Tomonori Hashiyama, Nathan Sorenson, Philippe Pasquier, Peter Mawhorter, Glen Takahashi, Gillian Smith and Robin Baumgarten (2011): The 2010 Mario AI championship: Level generation track. IEEE Transactions on Computational Intelligence and Games (in press)
Papers related to Turing Test track:
- J. Togelius, G. N. Yannakakis, S. Karakovskiy and N. Shaker: Assessing Believability , In Hingston (Ed.) Believablility in Computer Games, 2011. Springer-Verlag.
Papers used Mario AI benchmark:
The following list contains published work that has been using the benchmark:
- Diego Perez, Miguel Nicolau, Michael O'Neill, Anthony Brabazon: Evolving Behaviour Trees for the Mario AI Competition Using Grammatical Evolution. EvoApplications (1) 2011: 123-132
- S. Bojarski and C. Congdon: Realm: A rule-based evolutionary computation agent that learns to play mario. In Computational Intelligence and Games (CIG), 2010 IEEE Symposium, 2010.
If you have used the benchmark in your published work or if you are aware of any other papers that uses the benchmark please let us know by sending an email to Noor Shaker.