Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract)
Artificial Intelligence
2023-12-22 v1
Abstract
We develop a method of adapting the AlphaZero model to General Game Playing (GGP) that focuses on faster model generation and requires less knowledge to be extracted from the game rules. The dataset generation uses MCTS playing instead of self-play; only the value network is used, and attention layers replace the convolutional ones. This allows us to abandon any assumptions about the action space and board topology. We implement the method within the Regular Boardgames GGP system and show that we can build models outperforming the UCT baseline for most games efficiently.
Keywords
Cite
@article{arxiv.2312.14121,
title = {Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract)},
author = {Michał Maras and Michał Kępa and Jakub Kowalski and Marek Szykuła},
journal= {arXiv preprint arXiv:2312.14121},
year = {2023}
}
Comments
AAAI-24 Student Abstracts