Deep Learning for General Game Playing with Ludii and Polygames

by   Dennis J. N. J. Soemers, et al.

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.


page 1

page 2

page 3

page 4


Optimised Playout Implementations for the Ludii General Game System

This paper describes three different optimised implementations of playou...

Learning to Win by Reading Manuals in a Monte-Carlo Framework

Domain knowledge is crucial for effective performance in autonomous cont...

Playing Carcassonne with Monte Carlo Tree Search

Monte Carlo Tree Search (MCTS) is a relatively new sampling method with ...

Spatial State-Action Features for General Games

In many board games and other abstract games, patterns have been used as...

Elastic Monte Carlo Tree Search with State Abstraction for Strategy Game Playing

Strategy video games challenge AI agents with their combinatorial search...

Strategic Features for General Games

This short paper describes an ongoing research project that requires the...

Exploring Adaptive MCTS with TD Learning in miniXCOM

In recent years, Monte Carlo tree search (MCTS) has achieved widespread ...

Please sign up or login with your details

Forgot password? Click here to reset