Obserwuj
Philip Becker-Ehmck
Philip Becker-Ehmck
Volkswagen Group
Zweryfikowany adres z argmax.ai
Tytuł
Cytowane przez
Cytowane przez
Rok
Unsupervised real-time control through variational empowerment
M Karl, P Becker-Ehmck, M Soelch, D Benbouzid, P van der Smagt, ...
The International Symposium of Robotics Research, 158-173, 2019
552019
Switching Linear Dynamics for Variational Bayes Filtering
P Becker-Ehmck, J Peters, P van der Smagt
36th International Conference on Machine Learning (ICML), 2018
522018
Learning to Fly via Deep Model-Based Reinforcement Learning
P Becker-Ehmck, M Karl, J Peters, P van der Smagt
arXiv preprint arXiv:2003.08876, 2020
382020
Exploration via Empowerment Gain: Combining Novelty, Surprise and Learning Progress
P Becker-Ehmck, M Karl, J Peters, P van der Smagt
ICML 2021 Workshop on Unsupervised Reinforcement Learning, 2021
52021
Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
N Das, M Karl, P Becker-Ehmck, P van der Smagt
arXiv preprint arXiv:1911.00756, 2019
52019
Overcoming Knowledge Barriers: Online Imitation Learning from Observation with Pretrained World Models
X Zhang, P Becker-Ehmck, P van der Smagt, M Karl
arXiv preprint arXiv:2404.18896, 2024
2024
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
X Zhang, P Becker-Ehmck, P van der Smagt, M Karl
Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023
2023
Latent State-Space Models for Control
P Becker-Ehmck
Technische Universität Darmstadt, 2022
2022
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–8