| OCAtari: object-centric atari 2600 reinforcement learning environments Q Delfosse, J Blüml, B Gregori, S Sztwiertnia, K Kersting arXiv preprint arXiv:2306.08649, 2023 | 4 | 2023 |
| AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong J Blüml, J Czech, K Kersting Frontiers in artificial intelligence 6, 1014561, 2023 | 2 | 2023 |
| Representation Matters: The Game of Chess Poses a Challenge to Vision Transformers J Czech, J Blüml, K Kersting arXiv preprint arXiv:2304.14918, 2023 | 1 | 2023 |
| Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown C Derstroff, J Brugger, J Blüml, M Mezini, S Kramer, K Kersting arXiv preprint arXiv:2402.08511, 2024 | | 2024 |
| Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess F Helfenstein, J Blüml, J Czech, K Kersting arXiv preprint arXiv:2401.16852, 2024 | | 2024 |
| From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex? Y Keller, J Blüml, G Sudhakaran, K Kersting arXiv preprint arXiv:2311.13414, 2023 | | 2023 |
Kristian KerstingProfessor of AI & ML, TU Darmstadt, Co-Director hessian.ai, DFKI, Germany, CLAIRE & ELLISGeverifieerd e-mailadres voor cs.tu-darmstadt.de
