Game Engine Learning from Video

Abstract

Intelligent agents need to be able to make predictions about their environment. In this work we present a novel approach to learn a forward simulation model via simple search over pixel input. We make use of a video game, Super Mario Bros., as an initial test of our approach as it represents a physics system that is significantly less complex than reality. We demonstrate the significant improvement of our approach in predicting future states compared with a baseline CNN and apply the learned model to train a game playing agent. Thus we evaluate the algorithm in terms of the accuracy and value of its output model.

Cite

Text

Guzdial et al. "Game Engine Learning from Video." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/518

Markdown

[Guzdial et al. "Game Engine Learning from Video." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/guzdial2017ijcai-game/) doi:10.24963/IJCAI.2017/518

BibTeX

@inproceedings{guzdial2017ijcai-game,
  title     = {{Game Engine Learning from Video}},
  author    = {Guzdial, Matthew and Li, Boyang and Riedl, Mark O.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {3707-3713},
  doi       = {10.24963/IJCAI.2017/518},
  url       = {https://mlanthology.org/ijcai/2017/guzdial2017ijcai-game/}
}