Jannis Blüml

According to our database, Jannis Blüml authored at least 13 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Deep Reinforcement Learning Agents are not even close to Human Intelligence.

Quentin Delfosse, Jannis Blüml, Fabian Tatai, Théo Vincent, Bjarne Gregori, Elisabeth Dillies, Jan Peters, Constantin A. Rothkopf, Kristian Kersting

CoRR, May, 2025

Better Decisions through the Right Causal World Model.

Elisabeth Dillies, Quentin Delfosse, Jannis Blüml, Raban Emunds, Florian Peter Busch, Kristian Kersting

CoRR, April, 2025

Deep Reinforcement Learning via Object-Centric Attention.

Jannis Blüml, Cedric Derstroff, Bjarne Gregori, Elisabeth Dillies, Quentin Delfosse, Kristian Kersting

CoRR, April, 2025

Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions.

Can Cömer, Jannis Blüml, Cedric Derstroff, Kristian Kersting

CoRR, February, 2025

2024

OCALM: Object-Centric Assessment with Language Models.

Timo Kaufmann, Jannis Blüml, Antonia Wüst, Quentin Delfosse, Kristian Kersting, Eyke Hüllermeier

CoRR, 2024

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning.

Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Kristian Kersting

CoRR, 2024

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

Cedric Derstroff, Jannis Brugger, Jannis Blüml, Mira Mezini, Stefan Kramer, Kristian Kersting

CoRR, 2024

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

Felix Helfenstein, Jannis Blüml, Johannes Czech, Kristian Kersting

CoRR, 2024

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments.

Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Sebastian Sztwiertnia, Kristian Kersting

RLJ, 2024

Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers.

Johannes Czech, Jannis Blüml, Kristian Kersting, Hedinn Steingrimsson

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023

AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong.

Jannis Blüml, Johannes Czech, Kristian Kersting

Frontiers Artif. Intell., February, 2023

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

Yannik Keller, Jannis Blüml, Gopika Sudhakaran, Kristian Kersting

CoRR, 2023

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

Johannes Czech, Jannis Blüml, Kristian Kersting

CoRR, 2023