Deep Learning for Video Game Playing

Preprint English OPEN
Justesen, Niels ; Bontrager, Philip ; Togelius, Julian ; Risi, Sebastian (2017)
  • Subject: Computer Science - Artificial Intelligence
    acm: ComputingMilieux_PERSONALCOMPUTING

In this article, we review recent Deep Learning advances in the context of how they have been applied to play different types of video games such as first-person shooters, arcade games, and real-time strategy games. We analyze the unique requirements that different game genres pose to a deep learning system and highlight important open challenges in the context of applying these machine learning methods to video games, such as general game playing, dealing with extremely large decision spaces and sparse rewards.
  • References (125)
    125 references, page 1 of 13

    [1] S. Alvernaz and J. Togelius. Autoencoder-augmented neuroevolution for visual doom playing. In Computational Intelligence and Games (CIG), 2017 IEEE Conference on. IEEE, 2017.

    [2] C. Beattie, J. Z. Leibo, D. Teplyashin, T. Ward, M. Wainwright, H. Ku¨ttler, A. Lefrancq, S. Green, V. Valde´s, A. Sadik, et al. Deepmind lab. arXiv preprint arXiv:1612.03801, 2016.

    [3] M. Bellemare, Y. Naddaf, J. Veness, and M. Bowling. The arcade learning environment: An evaluation platform for general agents. In Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015.

    [4] M. Bellemare, S. Srinivasan, G. Ostrovski, T. Schaul, D. Saxton, and R. Munos. Unifying count-based exploration and intrinsic motivation. In Advances in Neural Information Processing Systems, pages 1471- 1479, 2016.

    [5] M. G. Bellemare, W. Dabney, and R. Munos. A distributional perspective on reinforcement learning. arXiv preprint arXiv:1707.06887, 2017.

    [6] M. G. Bellemare, Y. Naddaf, J. Veness, and M. Bowling. The arcade learning environment: An evaluation platform for general agents. J. Artif. Intell. Res.(JAIR), 47:253-279, 2013.

    [7] Y. Bengio, J. Louradour, R. Collobert, and J. Weston. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning, pages 41-48. ACM, 2009.

    [8] S. Bhatti, A. Desmaison, O. Miksik, N. Nardelli, N. Siddharth, and P. H. Torr. Playing doom with slam-augmented deep reinforcement learning. arXiv preprint arXiv:1612.00380, 2016.

    [9] N. Bhonker, S. Rozenberg, and I. Hubara. Playing snes in the retro learning environment. arXiv preprint arXiv:1611.02205, 2016.

    [10] M. Bogdanovic, D. Markovikj, M. Denil, and N. De Freitas. Deep apprenticeship learning for playing video games. In Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015.

  • Metrics
    No metrics available
Share - Bookmark