Deep Reinforcement Learning (DRL) reaches a superhuman level of play in many complete
information games. The state of the art search algorithm used in combination with DRL is …

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 …

In this paper, we use fully convolutional architectures in AlphaZero-like self-play training
setups to facilitate transfer between variants of board games as well as distinct games. We …

Local, spatial state-action features can be used to effectively train linear policies from self-
play in a wide variety of board games. Such policies can play games directly, or be used to …

There are several different game description languages (GDLs), each intended to allow
wide ranges of arbitrary games (ie, general games) to be described in a single higher-level …

In many board games and other abstract games, patterns have been used as features that
can guide automated game-playing agents. Such patterns or features often represent …

Monte Carlo Tree Search and Monte Carlo Search have good results for many combinatorial
problems. In this paper we propose to use Monte Carlo Search to design mathematical …

Abstract The Ludii AI Competition involves general game playing events focused on
developing agents that can play a wide variety of board games. In the 2022 edition, three …

The optimal level and progression of challenge are critical factors for delivering an
enjoyable gaming experience. In this study, I have developed a novel system that generates …

Making inferences with a deep neural network on a batch of states is much faster with a GPU
than making inferences on one state after another. We build on this property to propose …