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

Sebastian Trimpe

Local policy search with Bayesian optimization


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

Figure 1 for Local policy search with Bayesian optimization
Figure 2 for Local policy search with Bayesian optimization
Figure 3 for Local policy search with Bayesian optimization
Figure 4 for Local policy search with Bayesian optimization

  Access Paper or Ask Questions

GoSafe: Globally Optimal Safe Robot Learning


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

Figure 1 for GoSafe: Globally Optimal Safe Robot Learning
Figure 2 for GoSafe: Globally Optimal Safe Robot Learning
Figure 3 for GoSafe: Globally Optimal Safe Robot Learning
Figure 4 for GoSafe: Globally Optimal Safe Robot Learning

  Access Paper or Ask Questions

Safe Value Functions


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

Figure 1 for Safe Value Functions
Figure 2 for Safe Value Functions
Figure 3 for Safe Value Functions
Figure 4 for Safe Value Functions

  Access Paper or Ask Questions

Probabilistic robust linear quadratic regulators with Gaussian processes


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

Figure 1 for Probabilistic robust linear quadratic regulators with Gaussian processes
Figure 2 for Probabilistic robust linear quadratic regulators with Gaussian processes
* 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

Figure 1 for Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
Figure 2 for Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
Figure 3 for Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
Figure 4 for Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees

  Access Paper or Ask Questions

Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression


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

Figure 1 for Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression
Figure 2 for Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression
Figure 3 for Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression
Figure 4 for Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression
* Contains supplementary material 
  Access Paper or Ask Questions

Symplectic Gaussian Process Dynamics


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

Figure 1 for Symplectic Gaussian Process Dynamics
Figure 2 for Symplectic Gaussian Process Dynamics
Figure 3 for Symplectic Gaussian Process Dynamics
Figure 4 for Symplectic Gaussian Process Dynamics

  Access Paper or Ask Questions

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


Dec 11, 2020
A. René Geist, Sebastian Trimpe

Figure 1 for Structured learning of rigid-body dynamics: A survey and unified view
Figure 2 for Structured learning of rigid-body dynamics: A survey and unified view
Figure 3 for Structured learning of rigid-body dynamics: A survey and unified view
Figure 4 for Structured learning of rigid-body dynamics: A survey and unified view

  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

Figure 1 for Robot Learning with Crash Constraints
Figure 2 for Robot Learning with Crash Constraints
Figure 3 for Robot Learning with Crash Constraints
Figure 4 for Robot Learning with Crash Constraints
* 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

Figure 1 for Learning Event-triggered Control from Data through Joint Optimization
Figure 2 for Learning Event-triggered Control from Data through Joint Optimization
Figure 3 for Learning Event-triggered Control from Data through Joint Optimization
Figure 4 for Learning Event-triggered Control from Data through Joint Optimization

  Access Paper or Ask Questions

Identifying Causal Structure in Dynamical Systems


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

Figure 1 for Identifying Causal Structure in Dynamical Systems
Figure 2 for Identifying Causal Structure in Dynamical Systems
Figure 3 for Identifying Causal Structure in Dynamical Systems
Figure 4 for Identifying Causal Structure in Dynamical Systems

  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

Figure 1 for Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures
Figure 2 for Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures
Figure 3 for Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures
Figure 4 for Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures
* 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

Figure 1 for Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes
Figure 2 for Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes
Figure 3 for Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes
Figure 4 for Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes
* 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

Figure 1 for A Kernel Two-sample Test for Dynamical Systems
Figure 2 for A Kernel Two-sample Test for Dynamical Systems
Figure 3 for A Kernel Two-sample Test for Dynamical Systems
Figure 4 for A Kernel Two-sample Test for Dynamical Systems

  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

Figure 1 for Safe and Fast Tracking Control on a Robot Manipulator: Robust MPC and Neural Network Control
Figure 2 for Safe and Fast Tracking Control on a Robot Manipulator: Robust MPC and Neural Network Control
Figure 3 for Safe and Fast Tracking Control on a Robot Manipulator: Robust MPC and Neural Network Control
Figure 4 for Safe and Fast Tracking Control on a Robot Manipulator: Robust MPC and Neural Network Control
* 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

Figure 1 for Actively Learning Gaussian Process Dynamics
Figure 2 for Actively Learning Gaussian Process Dynamics
Figure 3 for Actively Learning Gaussian Process Dynamics

  Access Paper or Ask Questions

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


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

Figure 1 for Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
Figure 2 for Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
Figure 3 for Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
Figure 4 for Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
* 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

Figure 1 for A Learnable Safety Measure
Figure 2 for A Learnable Safety Measure
Figure 3 for A Learnable Safety Measure
* 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

Figure 1 for Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
Figure 2 for Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
Figure 3 for Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
Figure 4 for Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
* 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

Figure 1 for Trajectory-Based Off-Policy Deep Reinforcement Learning
Figure 2 for Trajectory-Based Off-Policy Deep Reinforcement Learning
Figure 3 for Trajectory-Based Off-Policy Deep Reinforcement Learning
Figure 4 for Trajectory-Based Off-Policy Deep Reinforcement Learning
* 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

Figure 1 for Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study
Figure 2 for Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study
Figure 3 for Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study
Figure 4 for Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study
* 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

Figure 1 for Event-triggered Learning for Resource-efficient Networked Control
Figure 2 for Event-triggered Learning for Resource-efficient Networked Control
Figure 3 for Event-triggered Learning for Resource-efficient Networked Control
Figure 4 for Event-triggered Learning for Resource-efficient Networked Control
* 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

Figure 1 for Deep Reinforcement Learning for Event-Triggered Control
Figure 2 for Deep Reinforcement Learning for Event-Triggered Control
Figure 3 for Deep Reinforcement Learning for Event-Triggered Control
Figure 4 for Deep Reinforcement Learning for Event-Triggered Control

  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

Figure 1 for Gait learning for soft microrobots controlled by light fields
Figure 2 for Gait learning for soft microrobots controlled by light fields
Figure 3 for Gait learning for soft microrobots controlled by light fields
Figure 4 for Gait learning for soft microrobots controlled by light fields
* 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

Figure 1 for Learning an Approximate Model Predictive Controller with Guarantees
Figure 2 for Learning an Approximate Model Predictive Controller with Guarantees
Figure 3 for Learning an Approximate Model Predictive Controller with Guarantees
* 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

Figure 1 for A Local Information Criterion for Dynamical Systems
Figure 2 for A Local Information Criterion for Dynamical Systems
Figure 3 for A Local Information Criterion for Dynamical Systems
Figure 4 for A Local Information Criterion for Dynamical Systems

  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

Figure 1 for Probabilistic Recurrent State-Space Models
Figure 2 for Probabilistic Recurrent State-Space Models
Figure 3 for Probabilistic Recurrent State-Space Models
Figure 4 for Probabilistic Recurrent State-Space Models

  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

Figure 1 for On the Design of LQR Kernels for Efficient Controller Learning
Figure 2 for On the Design of LQR Kernels for Efficient Controller Learning
Figure 3 for On the Design of LQR Kernels for Efficient Controller Learning
Figure 4 for On the Design of LQR Kernels for Efficient Controller Learning
* 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

Figure 1 for Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
Figure 2 for Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
Figure 3 for Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
Figure 4 for Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
* 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

Figure 1 for Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
Figure 2 for Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
Figure 3 for Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
Figure 4 for Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
* 7 pages, 6 figures, to appear in IEEE 2017 International Conference on Robotics and Automation (ICRA) 
  Access Paper or Ask Questions