Deep Learning for General Game Playing with Ludii and Polygames
This work addresses the bottleneck of manual configuration in automated game-playing systems, making it easier to apply state-of-the-art methods to a wide range of games without incremental improvements.
The paper tackles the problem of requiring game-specific domain knowledge for training deep learning models in general game playing by bridging Ludii and Polygames, enabling automatic determination of neural network input/output shapes for over 500 games and demonstrating results from short training runs across various board games.
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.