Research Interests
(hierarchical and model-based) reinforcement learning, offline reinforcement learning and imitation learning, machine learning for robotics
Short CV
- 2019-present: PhD student, Max Planck Institute for Intelligent Systems, University of Tuebingen
Selected Publications
- Wang Q, McCarthy R, Bulens D C, et al. Improving behavioural cloning with positive unlabeled learning[C]//Conference on Robot Learning. PMLR, 2023: 3851-3869.
- Gürtler N, Widmaier F, Sancaktar C, et al. Real robot challenge 2022: Learning dexterous manipulation from offline data in the real world[C]//NeurIPS 2022 Competition Track. PMLR, 2023: 133-150.
- Gürtler N, Blaes S, Kolev P, et al. Benchmarking offline reinforcement learning on real-robot hardware[J]. arXiv preprint arXiv:2307.15690, 2023.
- Pan H R, Gürtler N, Neitz A, et al. Direct advantage estimation[J]. Advances in Neural Information Processing Systems, 2022, 35: 11869-11880.
- Gürtler N, Büchler D, Martius G. Hierarchical reinforcement learning with timed subgoals[J]. Advances in Neural Information Processing Systems, 2021, 34: 21732-21743.