Picture for Jannis Blüml

Jannis Blüml

OCALM: Object-Centric Assessment with Language Models

Add code
Jun 24, 2024
Viaarxiv icon

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning

Add code
Jun 06, 2024
Viaarxiv icon

Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown

Add code
Feb 13, 2024
Viaarxiv icon

Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess

Add code
Jan 30, 2024
Viaarxiv icon

From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex?

Add code
Nov 22, 2023
Viaarxiv icon

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments

Add code
Jun 14, 2023
Viaarxiv icon

Representation Matters: The Game of Chess Poses a Challenge to Vision Transformers

Add code
Apr 28, 2023
Viaarxiv icon