Deep Learning for General Game Playing with Ludii and Polygames

TL;DR

This paper introduces a bridge between Ludii and Polygames, enabling deep learning models to be trained on over 500 Ludii games without game-specific adjustments, streamlining the development of general game-playing AI.

Contribution

It presents a novel integration that automates tensor shape determination for any Ludii game, removing the need for game-specific domain knowledge in deep learning models.

Findings

Successful training on diverse Ludii games with minimal setup

Automated tensor shape determination for new games

Potential for rapid development of general game-playing AI

Abstract

Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games. The training and search algorithms are not game-specific, but every individual game that these approaches are applied to still requires domain knowledge for the implementation of the game's rules, and constructing the neural network's architecture -- in particular the shapes of its input and output tensors. Ludii is a general game system that already contains over 500 different games, which can rapidly grow thanks to its powerful and user-friendly game description language. Polygames is a framework with training and search algorithms, which has already produced superhuman players for several board games. This paper describes the implementation of a bridge between Ludii and Polygames, which enables Polygames to train and evaluate models for games that are implemented and run through Ludii. We do not require any game-specific domain knowledge anymore, and instead leverage our domain knowledge of the Ludii system and its abstract state and move representations to write functions that can automatically determine the appropriate shapes for input and output tensors for any game implemented in Ludii. We describe experimental results for short training runs in a wide variety of different board games, and discuss several open problems and avenues for future research.