1 code implementation • 16 Mar 2023 • Jakub Kowalski, Elliot Doe, Mark H. M. Winands, Daniel Górski, Dennis J. N. J. Soemers
Furthermore, we extend this new algorithm to properly address games with draws, like Awari, by adding an additional layer of PNS on top of the MCTS tree.
no code implementations • 10 Jan 2023 • Matthew Stephenson, Dennis J. N. J. Soemers, Éric Piette, Cameron Browne
This paper presents a general approach for measuring distances between board games within the Ludii general game system.
no code implementations • 8 Jun 2022 • Elliot Doe, Mark H. M. Winands, Dennis J. N. J. Soemers, Cameron Browne
Proof-Number Search (PNS) and Monte-Carlo Tree Search (MCTS) have been successfully applied for decision making in a range of games.
no code implementations • 1 May 2022 • Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne
There are several different game description languages (GDLs), each intended to allow wide ranges of arbitrary games (i. e., general games) to be described in a single higher-level language than general-purpose programming languages.
no code implementations • 17 Jan 2022 • Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne
In many board games and other abstract games, patterns have been used as features that can guide automated game-playing agents.
1 code implementation • 22 Nov 2021 • Cameron Browne, Éric Piette, Matthew Stephenson, Dennis J. N. J. Soemers
Game boards are described in the Ludii general game system by their underlying graphs, based on tiling, shape and graph operators, with the automatic detection of important properties such as topological relationships between graph elements, directions and radial step sequences.
no code implementations • 4 Nov 2021 • Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne
This paper describes three different optimised implementations of playouts, as commonly used by game-playing algorithms such as Monte-Carlo Tree Search.
no code implementations • 20 Sep 2021 • Matthew Stephenson, Eric Piette, Dennis J. N. J. Soemers, Cameron Browne
In this paper we present a process for automatically generating manuals for board games within the Ludii general game system.
no code implementations • 2 Jul 2021 • Éric Piette, Matthew Stephenson, Dennis J. N. J. Soemers, Cameron Browne
Many games often share common ideas or aspects between them, such as their rules, controls, or playing area.
no code implementations • 26 May 2021 • Matthew Stephenson, Dennis J. N. J. Soemers, Eric Piette, Cameron Browne
This paper investigates the performance of different general-game-playing heuristics for games in the Ludii general game system.
no code implementations • 24 Feb 2021 • Dennis J. N. J. Soemers, Vegard Mella, Eric Piette, Matthew Stephenson, Cameron Browne, Olivier Teytaud
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.
1 code implementation • 23 Jan 2021 • Dennis J. N. J. Soemers, Vegard Mella, Cameron Browne, Olivier Teytaud
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.
1 code implementation • 6 Jan 2021 • Éric Piette, Cameron Browne, Dennis J. N. J. Soemers
This technical report outlines the fundamental workings of the game logic behind Ludii, a general game system, that can be used to play a wide variety of games.
no code implementations • 4 Jan 2021 • Cameron Browne, Dennis J. N. J. Soemers, Eric Piette
This short paper describes an ongoing research project that requires the automated self-play learning and evaluation of a large number of board games in digital form.
1 code implementation • 30 May 2020 • Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne
ExIt involves training a policy to mimic the search behaviour of a tree search algorithm - such as Monte-Carlo tree search - and using the trained policy to guide it.
no code implementations • 29 Jun 2019 • Matthew Stephenson, Éric Piette, Dennis J. N. J. Soemers, Cameron Browne
Ludii is a general game system being developed as part of the ERC-funded Digital Ludeme Project (DLP).
no code implementations • 29 Jun 2019 • Cédric Piette, Éric Piette, Matthew Stephenson, Dennis J. N. J. Soemers, Cameron Browne
Many of the famous single-player games, commonly called puzzles, can be shown to be NP-Complete.
no code implementations • 29 Jun 2019 • Éric Piette, Matthew Stephenson, Dennis J. N. J. Soemers, Cameron Browne
Although General Game Playing (GGP) systems can facilitate useful research in Artificial Intelligence (AI) for game-playing, they are often computationally inefficient and somewhat specialised to a specific class of games.
no code implementations • 29 Jun 2019 • Matthew Stephenson, Éric Piette, Dennis J. N. J. Soemers, Cameron Browne
The Digital Ludeme Project (DLP) aims to reconstruct and analyse over 1000 traditional strategy games using modern techniques.
no code implementations • 31 May 2019 • Cameron Browne, Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Michael Conrad, Walter Crist, Thierry Depaulis, Eddie Duggan, Fred Horn, Steven Kelk, Simon M. Lucas, João Pedro Neto, David Parlett, Abdallah Saffidine, Ulrich Schädler, Jorge Nuno Silva, Alex de Voogt, Mark H. M. Winands
Digital Archaeoludology (DAL) is a new field of study involving the analysis and reconstruction of ancient games from incomplete descriptions and archaeological evidence using modern computational techniques.
no code implementations • 14 May 2019 • Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne
In recent years, state-of-the-art game-playing agents often involve policies that are trained in self-playing processes where Monte Carlo tree search (MCTS) algorithms and trained policies iteratively improve each other.
1 code implementation • 13 May 2019 • Éric Piette, Dennis J. N. J. Soemers, Matthew Stephenson, Chiara F. Sironi, Mark H. M. Winands, Cameron Browne
While current General Game Playing (GGP) systems facilitate useful research in Artificial Intelligence (AI) for game-playing, they are often somewhat specialised and computationally inefficient.
1 code implementation • 21 Mar 2019 • Dennis J. N. J. Soemers, Éric Piette, Cameron Browne
This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games.