Andreas Doerr
Andreas Doerr
Research Scientist, Bosch Center for Artificial Intelligence, Max Planck Institut IS
Bestätigte E-Mail-Adresse bei tuebingen.mpg.de - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Probabilistic recurrent state-space models
A Doerr, C Daniel, M Schiegg, D Nguyen-Tuong, S Schaal, M Toussaint, ...
arXiv preprint arXiv:1801.10395, 2018
422018
Direct Loss Minimization Inverse Optimal Control.
A Doerr, ND Ratliff, J Bohg, M Toussaint, S Schaal
Robotics: Science and Systems, 2015
372015
Optimizing long-term predictions for model-based policy search
A Doerr, C Daniel, D Nguyen-Tuong, A Marco, S Schaal, T Marc, S Trimpe
Conference on Robot Learning, 227-238, 2017
262017
Model-based policy search for automatic tuning of multivariate PID controllers
A Doerr, D Nguyen-Tuong, A Marco, S Schaal, S Trimpe
2017 IEEE International Conference on Robotics and Automation (ICRA), 5295-5301, 2017
152017
Learning gaussian processes by minimizing pac-bayesian generalization bounds
D Reeb, A Doerr, S Gerwinn, B Rakitsch
Advances in Neural Information Processing Systems, 3337-3347, 2018
72018
Monte carlo methods in uncertainity quantification
A Dörr, M Mögerle, M Schneider
Journal of Statistical Computation and Simulation 58 (2), 99-120, 2014
52014
Meta-learning acquisition functions for bayesian optimization
M Volpp, L Fröhlich, A Doerr, F Hutter, C Daniel
arXiv preprint arXiv:1904.02642, 2019
32019
Trajectory-Based Off-Policy Deep Reinforcement Learning
A Doerr, M Volpp, M Toussaint, S Trimpe, C Daniel
International Conference on Machine Learning, 2019
22019
Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
M Volpp, LP Fröhlich, K Fischer, A Doerr, S Falkner, F Hutter, C Daniel
arXiv preprint arXiv:1904.02642, 2019
12019
Adaptive and Learning Concepts in Hydraulic Force Control
A Doerr
Universität Stuttgart Stuttgart, 2015
2015
Policy search for imitation learning
A Doerr
2015
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–11