General Video Game AI: Learning from Screen Capture

Preprint English OPEN
Kunanusont, Kamolwan ; Lucas, Simon M. ; Perez-Liebana, Diego (2017)
  • Subject: Computer Science - Artificial Intelligence
    acm: ComputingMilieux_PERSONALCOMPUTING

General Video Game Artificial Intelligence is a general game playing framework for Artificial General Intelligence research in the video-games domain. In this paper, we propose for the first time a screen capture learning agent for General Video Game AI framework. A Deep Q-Network algorithm was applied and improved to develop an agent capable of learning to play different games in the framework. After testing this algorithm using various games of different categories and difficulty levels, the results suggest that our proposed screen capture learning agent has the potential to learn many different games using only a single learning algorithm.
  • References (26)
    26 references, page 1 of 3

    [1] S. M. Lucas, “Ms Pac-man Competition,” ACM SIGEVOlution, vol. 2, no. 4, pp. 37-38, 2007.

    [2] J. Togelius, S. Karakovskiy, and R. Baumgarten, “The 2009 Mario AI Competition,” in IEEE Congress on Evolutionary Computation, pp. 1-8, IEEE, 2010.

    [3] B. Goertzel and C. Pennachin, Artificial General Intelligence, vol. 2. Springer, 2007.

    [4] D. Perez, S. Samothrakis, J. Togelius, T. Schaul, S. Lucas, A. Coue¨toux, J. Lee, C.-U. Lim, and T. Thompson, “The 2014 General Video Game Playing Competition,” 2015.

    [5] J. Levine, C. B. Congdon, M. Ebner, G. Kendall, S. M. Lucas, R. Miikkulainen, T. Schaul, and T. Thompson, “General Video Game Playing,” Dagstuhl Follow-Ups, vol. 6, 2013.

    [6] T. Schaul, “A Video Game Description Language for Model-based or Interactive Learning,” in Computational Intelligence in Games (CIG), 2013 IEEE Conference on, pp. 1-8, IEEE, 2013.

    [7] S. M. Lucas, “Ms. Pac-man Competition: Screen Capture Version.” http://cswww.essex.ac.uk/staff/sml/pacman/PacManContest.html, 2007. Accessed: 2016-12-31.

    [8] M. Kempka, M. Wydmuch, G. Runc, J. Toczek, and W. Jas´kowski, “ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning,” arXiv preprint arXiv:1605.02097, 2016.

    [9] V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, et al., “Human-level Control through Deep Reinforcement Learning,” Nature, vol. 518, no. 7540, pp. 529-533, 2015.

    [10] M. G. Bellemare, Y. Naddaf, J. Veness, and M. Bowling, “The Arcade Learning Environment: An Evaluation Platform for General Agents,” Journal of Artificial Intelligence Research, 2012.

  • Metrics
    No metrics available
Share - Bookmark