Deep Reinforcement Learning for General Game Playing

Abstract

General Game Playing agents are required to play games they have never seen before simply by looking at a formal description of the rules of the game at runtime. Previous successful agents have been based on search with generic heuristics, with almost no work done into using machine learning. Recent advances in deep reinforcement learning have shown it to be successful in some two-player zero-sum board games such as Chess and Go. This work applies deep reinforcement learning to General Game Playing, extending the AlphaZero algorithm and finds that it can provide competitive results.

Cite

Text

Goldwaser and Thielscher. "Deep Reinforcement Learning for General Game Playing." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I02.5533

Markdown

[Goldwaser and Thielscher. "Deep Reinforcement Learning for General Game Playing." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/goldwaser2020aaai-deep/) doi:10.1609/AAAI.V34I02.5533

BibTeX

@inproceedings{goldwaser2020aaai-deep,
  title     = {{Deep Reinforcement Learning for General Game Playing}},
  author    = {Goldwaser, Adrian and Thielscher, Michael},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {1701-1708},
  doi       = {10.1609/AAAI.V34I02.5533},
  url       = {https://mlanthology.org/aaai/2020/goldwaser2020aaai-deep/}
}