no code implementations • 13 Feb 2024 • Cedric Derstroff, Jannis Brugger, Jannis Blüml, Mira Mezini, Stefan Kramer, Kristian Kersting
It strategically allocates computational resources to focus on promising segments of the search tree, making it a very attractive search algorithm in large search spaces.
1 code implementation • 30 Jan 2024 • Felix Helfenstein, Jannis Blüml, Johannes Czech, Kristian Kersting
This paper presents a new approach that integrates deep learning with computational chess, using both the Mixture of Experts (MoE) method and Monte-Carlo Tree Search (MCTS).
1 code implementation • 22 Nov 2023 • Yannik Keller, Jannis Blüml, Gopika Sudhakaran, Kristian Kersting
The gameplay of strategic board games such as chess, Go and Hex is often characterized by combinatorial, relational structures -- capturing distinct interactions and non-local patterns -- and not just images.
1 code implementation • 14 Jun 2023 • Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Sebastian Sztwiertnia, Kristian Kersting
In our work, we extend the Atari Learning Environments, the most-used evaluation framework for deep RL approaches, by introducing OCAtari, that performs resource-efficient extractions of the object-centric states for these games.
no code implementations • 28 Apr 2023 • Johannes Czech, Jannis Blüml, Kristian Kersting
While transformers have gained the reputation as the "Swiss army knife of AI", no one has challenged them to master the game of chess, one of the classical AI benchmarks.