43 citations · 99 across the 31 of their papers we have counts for
36 papers
Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners
David Milec, Spyridon Samothrakis, Michael Fairbank +1
The dominance of Neural Networks (NNs) in RL is partially due to their incremental learning capability, which naturally suits the online, non-stationary nature of self-play trainin…
For How Long Should We Be Punching? Learning Action Duration in Fighting Games
Hoang Hai Nguyen, Kurt Driessens, Dennis J. N. J. Soemers
Fighting games such as Street Fighter II present unique challenges to reinforcement learning (RL) agents due to their fast-paced, real-time nature. In most RL frameworks, agents ar…
StratFormer: Adaptive Opponent Modeling and Exploitation in Imperfect-Information Games
Andy Caen, Mark H. M. Winands, Dennis J. N. J. Soemers
We present StratFormer, a transformer-based meta-agent that learns to simultaneously model and exploit opponents in imperfect-information games through a two-phase curriculum. The…
Best Agent Identification for General Game Playing
Matthew Stephenson, Alex Newcombe, Eric Piette +1
We present an efficient and generalised procedure to accurately identify the best (or near best) performing algorithm for each sub-task in a multi-problem domain. Our approach trea…
Generalized Proof-Number Monte-Carlo Tree Search
Jakub Kowalski, Dennis J. N. J. Soemers, Szymon Kosakowski +1
This paper presents Generalized Proof-Number Monte-Carlo Tree Search: a generalization of recently proposed combinations of Proof-Number Search (PNS) with Monte-Carlo Tree Search (…
Ludax: A GPU-Accelerated Domain Specific Language for Board Games
Graham Todd, Alexander G. Padula, Dennis J. N. J. Soemers +1
Games have long been used as benchmarks and testing environments for research in artificial intelligence. A key step in supporting this research was the development of game descrip…
A Research Agenda for Usability and Generalisation in Reinforcement Learning
Dennis J. N. J. Soemers, Spyridon Samothrakis, Kurt Driessens +1
It is common practice in reinforcement learning (RL) research to train and deploy agents in bespoke simulators, typically implemented by engineers directly in general-purpose progr…
Anytime Sequential Halving in Monte-Carlo Tree Search
Dominic Sagers, Mark H. M. Winands, Dennis J. N. J. Soemers
Monte-Carlo Tree Search (MCTS) typically uses multi-armed bandit (MAB) strategies designed to minimize cumulative regret, such as UCB1, as its selection strategy. However, in the r…
Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards
Alexander G. Padula, Dennis J. N. J. Soemers
Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigat…
Enhancements for Real-Time Monte-Carlo Tree Search in General Video Game Playing
Dennis J. N. J. Soemers, Chiara F. Sironi, Torsten Schuster +1
General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of real-time video games that are unknown in advance. This limits the use of dom…
GAVEL: Generating Games Via Evolution and Language Models
Graham Todd, Alexander Padula, Matthew Stephenson +3
Automatically generating novel and interesting games is a complex task. Challenges include representing game rules in a computationally workable form, searching through the large s…
Games of Knightian Uncertainty as AGI testbeds
Spyridon Samothrakis, Dennis J. N. J. Soemers, Damian Machlanski
Arguably, for the latter part of the late 20th and early 21st centuries, games have been seen as the drosophila of AI. Games are a set of exciting testbeds, whose solutions (in ter…
Towards a Characterisation of Monte-Carlo Tree Search Performance in Different Games
Dennis J. N. J. Soemers, Guillaume Bams, Max Persoon +5
Many enhancements to Monte-Carlo Tree Search (MCTS) have been proposed over almost two decades of general game playing and other artificial intelligence research. However, our abil…
Proof Number Based Monte-Carlo Tree Search
Jakub Kowalski, Elliot Doe, Mark H. M. Winands +2
This paper proposes a new game-search algorithm, PN-MCTS, which combines Monte-Carlo Tree Search (MCTS) and Proof-Number Search (PNS). These two algorithms have been successfully a…
Measuring Board Game Distance
Matthew Stephenson, Dennis J. N. J. Soemers, Éric Piette +1
This paper presents a general approach for measuring distances between board games within the Ludii general game system. These distances are calculated using a previously published…
Combining Monte-Carlo Tree Search with Proof-Number Search
Elliot Doe, Mark H. M. Winands, Dennis J. N. J. Soemers +1
Proof-Number Search (PNS) and Monte-Carlo Tree Search (MCTS) have been successfully applied for decision making in a range of games. This paper proposes a new approach called PN-MC…
The Ludii Game Description Language is Universal
Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson +1
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…
Spatial State-Action Features for General Games
Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson +1
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 particular…
General Board Geometry
Cameron Browne, Éric Piette, Matthew Stephenson +1
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 propert…
Optimised Playout Implementations for the Ludii General Game System
Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson +1
This paper describes three different optimised implementations of playouts, as commonly used by game-playing algorithms such as Monte-Carlo Tree Search. Each of the optimised imple…
Automatic Generation of Board Game Manuals
Matthew Stephenson, Eric Piette, Dennis J. N. J. Soemers +1
In this paper we present a process for automatically generating manuals for board games within the Ludii general game system. This process requires many different sub-tasks to be a…
General Board Game Concepts
Éric Piette, Matthew Stephenson, Dennis J. N. J. Soemers +1
Many games often share common ideas or aspects between them, such as their rules, controls, or playing area. However, in the context of General Game Playing (GGP) for board games,…
General Game Heuristic Prediction Based on Ludeme Descriptions
Matthew Stephenson, Dennis J. N. J. Soemers, Eric Piette +1
This paper investigates the performance of different general-game-playing heuristics for games in the Ludii general game system. Based on these results, we train several regression…
Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants
Dennis J. N. J. Soemers, Vegard Mella, Eric Piette +3
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…