Follow
Maximilian Karl
Maximilian Karl
Research Scientist, Machine Learning Research Lab, Volkswagen Group
Verified email at in.tum.de
Title
Cited by
Cited by
Year
Deep variational bayes filters: Unsupervised learning of state space models from raw data
M Karl, M Soelch, J Bayer, P van der Smagt
arXiv preprint arXiv:1605.06432, 2016
4422016
Stable reinforcement learning with autoencoders for tactile and visual data
H van Hoof, N Chen, M Karl, P van der Smagt, J Peters
2016 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2016
1872016
Dynamic movement primitives in latent space of time-dependent variational autoencoders
N Chen, M Karl, P van der Smagt
2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids …, 2016
752016
Unsupervised real-time control through variational empowerment
M Karl, P Becker-Ehmck, M Soelch, D Benbouzid, P Smagt, J Bayer
The International Symposium of Robotics Research, 158-173, 2019
592019
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
442020
Variational Inference with Hamiltonian Monte Carlo
C Wolf, M Karl, P van der Smagt
arXiv preprint arXiv:1609.08203, 2016
442016
Efficient Empowerment
M Karl, J Bayer, P van der Smagt
arXiv preprint arXiv:1509.08455, 2015
122015
On the role of the action space in robot manipulation learning and sim-to-real transfer
E Aljalbout, F Frank, M Karl, P van der Smagt
arXiv preprint arXiv:2312.03673, 2023
112023
Continuum worm-like robotic mechanism with decentral control architecture
M Eder, M Karl, A Knoll, S Riesner
2014 IEEE International Conference on Automation Science and Engineering …, 2014
92014
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
62021
Fast adaptive weight noise
J Bayer, M Karl, D Korhammer, P van der Smagt
arXiv preprint arXiv:1507.05331, 2015
62015
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
CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces
E Aljalbout, M Karl, P van der Smagt
arXiv preprint arXiv:2211.15824, 2022
42022
Unsupervised preprocessing for Tactile Data
M Karl, J Bayer, P van der Smagt
arXiv preprint arXiv:1606.07312, 2016
42016
Design of an inherently safe worm-like robot
M Eder, M Karl, F Schultheiß, J Schürmann, A Knoll, S Riesner
2013 IEEE International Symposium on Safety, Security, and Rescue Robotics …, 2013
42013
Compliant worm-like robotic mechanism with decentrally controlled pneumatic artificial muscles
M Eder, M Karl, A Knoll, S Riesner
2012 First International Conference on Innovative Engineering Systems, 243-248, 2012
42012
ML-based tactile sensor calibration: A universal approach
M Karl, A Lohrer, D Shah, F Diehl, M Fiedler, S Ognawala, J Bayer, ...
arXiv preprint arXiv:1606.06588, 2016
22016
Improving approximate RPCA with a K-sparsity prior
M Karl, C Osendorfer
arXiv preprint arXiv:1412.8291, 2014
22014
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
X Zhang, P Becker-Ehmck, P van der Smagt, M Karl
Workshop on Reincarnating Reinforcement Learning at ICLR 2023, 2023
12023
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
The system can't perform the operation now. Try again later.
Articles 1–20