Learning Levels of Mario AI Using Genetic Algorithms

  • Alejandro BaldominosEmail author
  • Yago Saez
  • Gustavo Recio
  • Javier Calle
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9422)


This paper introduces an approach based on Genetic Algorithms to learn levels from the Mario AI simulator, based on the Infinite Mario Bros. game (which is, at the same time, based on the Super Mario World game from Nintendo). In this approach, an autonomous agent playing Mario is able to learn a sequence of actions in order to maximize the score, not looking at the current state of the game at each time.

Different parameters for the Genetic Algorithm are explored, and two different stages are executed: in the first, domain independent genetic operators are used; while in the second knowledge about the domain is incorporated to these operators in order to improve the results.

Results are encouraging, as Mario is able to complete very difficult levels full of enemies, resembling the behavior of an expert human player.


Mario AI Games Genetic algorithms Learning 



This research work is co-funded by the Spanish Ministry of Industry, Tourism and Commerce under grant agreement no. TSI-090302-2011-11. Special acknowledgements are addressed at Hector Valero due to his contributions to the work.


  1. 1.
    Mario AI Championship 2010: Results (2010). Accessed 24 May 2015
  2. 2.
    Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. JAIR 47, 253–279 (2013)Google Scholar
  3. 3.
    Emgallar: Intelligent NPC for Mario AI Championship (2011). Accessed 22 May 2015
  4. 4.
    Fujii, N., Sato, Y., Wakama, H., Katayose, H.: Autonomously acquiring a video game agent’s behavior: letting players feel like playing with a human player. In: Nijholt, A., Romão, T., Reidsma, D. (eds.) ACE 2012. LNCS, vol. 7624, pp. 490–493. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  5. 5.
    Fujii, N., Sato, Y., Wakama, H., Kazai, K., Katayose, H.: Evaluating human-like behaviors of video-game agents autonomously acquired with biological constraints. In: Reidsma, D., Katayose, H., Nijholt, A. (eds.) ACE 2013. LNCS, vol. 8253, pp. 61–76. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  6. 6.
    Karakovskiy, S., Togelius, J.: The Mario AI benchmark and competitions. IEEE Trans. Comput. Intell. AI Games 4(1), 55–67 (2012)CrossRefGoogle Scholar
  7. 7.
    Meffert, K., Rotstan, N.: JGAP: Java Genetic Algorithms Package (2015). Accessed 6 July 2015
  8. 8.
    Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A., Veness, J., Graves, A., Riedmiller, M., Fidjeland, A., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)CrossRefGoogle Scholar
  9. 9.
    Steadman, I.: This AI ‘Solves’ Super Mario Bros. and Other Classic NES Games (2013). Accessed 22 May 2015
  10. 10.
    Togelius, J., Karakovskiy, S., Baumgarten, R.: The 2009 Mario AI competition. In: 2010 IEEE Congress on Evolutionary Computation, pp. 1–8 (2010)Google Scholar
  11. 11.
    Togelius, J., Karakovskiy, S., Koutnik, J., Schmidhuber, J.: Super Mario evolution. In: 2009 IEEE Symposium on Computational Intelligence and Games, pp. 156–161 (2009)Google Scholar
  12. 12.
    Valero, H., Saez, Y., Recio, G.: Computacin Evolutiva Aplicada al Desarrollo de Videojuegos: Mario AI (2011).

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Alejandro Baldominos
    • 1
    Email author
  • Yago Saez
    • 1
  • Gustavo Recio
    • 1
  • Javier Calle
    • 1
  1. 1.Universidad Carlos III de MadridLeganesSpain

Personalised recommendations