Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Sebastian Trimpe

Local policy search with Bayesian optimization


Jun 22, 2021
Sarah MĂĽller, Alexander von Rohr, Sebastian Trimpe


  Access Paper or Ask Questions

GoSafe: Globally Optimal Safe Robot Learning


May 27, 2021
Dominik Baumann, Alonso Marco, Matteo Turchetta, Sebastian Trimpe


  Access Paper or Ask Questions

Safe Value Functions


May 25, 2021
Pierre-François Massiani, Steve Heim, Friedrich Solowjow, Sebastian Trimpe


  Access Paper or Ask Questions

Probabilistic robust linear quadratic regulators with Gaussian processes


May 17, 2021
Alexander von Rohr, Matthias Neumann-Brosig, Sebastian Trimpe

* to be published in the proceedings of the 3rd Conference on Learning for Dynamics and Control 

  Access Paper or Ask Questions

Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees


May 07, 2021
Christian Fiedler, Carsten W. Scherer, Sebastian Trimpe


  Access Paper or Ask Questions

Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression


May 06, 2021
Christian Fiedler, Carsten W. Scherer, Sebastian Trimpe

* Contains supplementary material 

  Access Paper or Ask Questions

Symplectic Gaussian Process Dynamics


Feb 02, 2021
Katharina Ensinger, Friedrich Solowjow, Michael Tiemann, Sebastian Trimpe


  Access Paper or Ask Questions

Structured learning of rigid-body dynamics: A survey and unified view


Dec 11, 2020
A. René Geist, Sebastian Trimpe


  Access Paper or Ask Questions

Robot Learning with Crash Constraints


Oct 16, 2020
Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe

* 8 pages, 5 figures, 1 table, 1 algorithm. Under review. Video demonstration of the experiments available at https://youtu.be/RAiIo0l6_rE . Algorithm implementation available at https://github.com/alonrot/classified_regression.git 

  Access Paper or Ask Questions

Learning Event-triggered Control from Data through Joint Optimization


Aug 11, 2020
Niklas Funk, Dominik Baumann, Vincent Berenz, Sebastian Trimpe


  Access Paper or Ask Questions

Identifying Causal Structure in Dynamical Systems


Jun 06, 2020
Dominik Baumann, Friedrich Solowjow, Karl H. Johansson, Sebastian Trimpe


  Access Paper or Ask Questions

Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures


May 15, 2020
Alonso Marco, Alexander von Rohr, Dominik Baumann, José Miguel Hernández-Lobato, Sebastian Trimpe

* 14 pages, 4 figures, submitted 

  Access Paper or Ask Questions

Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes


Apr 23, 2020
A. Rene Geist, Sebastian Trimpe

* To be published in 2nd Annual Conference on Learning for Dynamics and Control (L4DC), Proceedings of Machine Learning Research 2020 

  Access Paper or Ask Questions

A Kernel Two-sample Test for Dynamical Systems


Apr 23, 2020
Friedrich Solowjow, Dominik Baumann, Christian Fiedler, Andreas Jocham, Thomas Seel, Sebastian Trimpe


  Access Paper or Ask Questions

Safe and Fast Tracking Control on a Robot Manipulator: Robust MPC and Neural Network Control


Dec 22, 2019
Julian Nubert, Johannes Köhler, Vincent Berenz, Frank Allgöwer, Sebastian Trimpe

* 8 pages, 4 figures, submitted to the Robotics and Automation Letters and to the International Conference on Robotics and Automation 

  Access Paper or Ask Questions

Actively Learning Gaussian Process Dynamics


Nov 22, 2019
Mona Buisson-Fenet, Friedrich Solowjow, Sebastian Trimpe


  Access Paper or Ask Questions

Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization


Oct 29, 2019
Matteo Turchetta, Andreas Krause, Sebastian Trimpe

* Submitted to IEEE Conference on Robotics and Automation 2020 (ICRA) 

  Access Paper or Ask Questions

A Learnable Safety Measure


Oct 07, 2019
Steve Heim, Alexander von Rohr, Sebastian Trimpe, Alexander Badri-Spröwitz

* 10 pages, Conference on Robot Learning CoRL 2019, 3 figures 

  Access Paper or Ask Questions

Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties


Jul 24, 2019
Alonso Marco, Dominik Baumann, Philipp Hennig, Sebastian Trimpe

* Submitted to Journal (under review) 

  Access Paper or Ask Questions

Trajectory-Based Off-Policy Deep Reinforcement Learning


May 14, 2019
Andreas Doerr, Michael Volpp, Marc Toussaint, Sebastian Trimpe, Christian Daniel

* Includes appendix. Accepted for ICML 2019 

  Access Paper or Ask Questions

Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study


Dec 18, 2018
Matthias Neumann-Brosig, Alonso Marco, Dieter Schwarzmann, Sebastian Trimpe

* 11 pages, 7 figures and 4 tables. To appear in IEEE Transactions on Control Systems Technology 

  Access Paper or Ask Questions

Event-triggered Learning for Resource-efficient Networked Control


Sep 27, 2018
Friedrich Solowjow, Dominik Baumann, Jochen Garcke, Sebastian Trimpe

* 7 pages, 4 figures, to appear in the 2018 American Control Conference (ACC) 

  Access Paper or Ask Questions

Deep Reinforcement Learning for Event-Triggered Control


Sep 13, 2018
Dominik Baumann, Jia-Jie Zhu, Georg Martius, Sebastian Trimpe


  Access Paper or Ask Questions

Gait learning for soft microrobots controlled by light fields


Sep 10, 2018
Alexander von Rohr, Sebastian Trimpe, Alonso Marco, Peer Fischer, Stefano Palagi

* 8 pages, 7 figures, to appear in the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems 2018 

  Access Paper or Ask Questions

Learning an Approximate Model Predictive Controller with Guarantees


Jun 11, 2018
Michael Hertneck, Johannes Köhler, Sebastian Trimpe, Frank Allgöwer

* 6 pages, 3 figures, to appear in IEEE Control Systems Letters 

  Access Paper or Ask Questions

A Local Information Criterion for Dynamical Systems


May 27, 2018
Arash Mehrjou, Friedrich Solowjow, Sebastian Trimpe, Bernhard Schölkopf


  Access Paper or Ask Questions

Probabilistic Recurrent State-Space Models


Feb 10, 2018
Andreas Doerr, Christian Daniel, Martin Schiegg, Duy Nguyen-Tuong, Stefan Schaal, Marc Toussaint, Sebastian Trimpe


  Access Paper or Ask Questions

On the Design of LQR Kernels for Efficient Controller Learning


Sep 20, 2017
Alonso Marco, Philipp Hennig, Stefan Schaal, Sebastian Trimpe

* 8 pages, 5 figures, to appear in 56th IEEE Conference on Decision and Control (CDC 2017) 

  Access Paper or Ask Questions

Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers


Mar 08, 2017
Andreas Doerr, Duy Nguyen-Tuong, Alonso Marco, Stefan Schaal, Sebastian Trimpe

* Accepted final version to appear in 2017 IEEE International Conference on Robotics and Automation (ICRA) 

  Access Paper or Ask Questions

Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization


Mar 03, 2017
Alonso Marco, Felix Berkenkamp, Philipp Hennig, Angela P. Schoellig, Andreas Krause, Stefan Schaal, Sebastian Trimpe

* 7 pages, 6 figures, to appear in IEEE 2017 International Conference on Robotics and Automation (ICRA) 

  Access Paper or Ask Questions