Nov 01, 2024 | Next week, I’ll be at the 2024 Conference on Robot Learning, representing the Robotics Institute Germany in the exhibition hall. We’ll also be presenting our work on Latent Action Priors From a Single Gait Cycle Demonstration for Online Imitation Learning at the LocoLearn: From Bioinspired Gait Generation to Active Perception workshop, and Fine-Tuning of Neural Network Approximate MPC without Retraining via Bayesian Optimization at the SAFE-ROL: Safe and Robust Robot Learning for Operation in the Real World workshop. |
Oct 20, 2024 | I’m excited to be presenting our new work on Viability of Future Actions: Robust Reinforcement Learning via Entropy Regularization at the European Workshop on Reinforcement Learning in Toulouse, France, from 28-30 October 2024. Looking forward to great discussions! |
Apr 08, 2024 | Our new paper on Local Bayesian Optimization for Controller Tuning with Crash Constraints has been published in the journal at - Automatisierungstechnik. |
Apr 01, 2024 | I started a new position with the Learning Systems and Robotics Lab at the Technical University of Munich. |
Mar 06, 2024 | Our new paper on Discovering Model Structure of Dynamical Systems with Combinatorial Bayesian Optimization has been published at the Transactions on Machine Learning Research. |
Jul 18, 2023 | Today we present our work on Experience Transfer for Robust Direct Data-Driven Control at the poster session of the RWTH Aachen AI Colloquium. |
Jun 29, 2023 | Have you ever wondered how to make your data-driven controllers more robust to variations? We just published a preprint on this topic Experience Transfer for Robust Direct Data-Driven Control. |
Jun 27, 2023 | We have significantly improved our preprint Event-Triggered Time-Varying Bayesian Optimization. You find the new version on arXiv. |
May 13, 2023 | Today I gave a talk on Local Search with Bayesian Gradient Estimates at the kick-off event for the Center for Algorithmics and Optimization at the RWTH Aachen University. |
Mar 02, 2023 | I am thrilled to share that my former Master’s student and now colleague, Paul Brunzema, has won the 2022 student award of the SEW-EURODRIVE Foundation for our work on Learning and Forgetting in Time-Varying Bayesian Optimization. |
Feb 22, 2023 | I recently attended the 57th Control Engineering Colloquium in Boppard and it was a nice platform to share my research and discuss with other researchers in the field. I’m happy to announce that my presentation was chosen as the runner-up for the best presentation award, making the experience even more rewarding. |
Nov 29, 2022 | I’m excited to share that today I gave a talk on Local Policy Search with Bayesian Gradient Estimates at the Research Seminar on Artificial Intelligence, which was organized by the RWTH Center for Artificial Intelligence. |
Aug 24, 2022 | Today we published Event-Triggered Time-Varying Bayesian Optimization on arXiv. The paper is about a finding the optimum of a time-varying objective function. |
Jul 15, 2022 | Our two submissions Improving the Performance of Robust Control through Event-Triggered Learning and On Controller Tuning with Time-Varying Bayesian Optimization for the IEEE Conference on Decision and Control (CDC) were accepted. We will present the papers at the Invited Session on Learning-based Control. |
Sep 28, 2021 | Our paper on Local policy search with Bayesian optimization got accepted at NeurIPS 2021 😊. |
Jun 23, 2021 | Yesterday we published a preprint on Local policy search with Bayesian optimization. It is about active sampling for policy gradients without access to a first-order oracle. |
Jun 07, 2021 | I presented our paper Probabilistic robust linear quadratic regulators with Gaussian processes at the poster session of the the 3rd Annual Learning for Dynamics & Control Conference. Thanks to everyone who stopped by 😀. |
Mar 06, 2021 | Our paper Probabilistic robust linear quadratic regulators with Gaussian processes was accepted at the 3rd Annual Learning for Dynamics & Control Conference. |
Feb 05, 2021 | I attended the EECI International Graduate School on Control course From Data to Decisions: the Scenario Approach by Marco C. Campi and Simone Garatti. It was a blast 😀. |