Our Paper, Time-Efficient Reinforcement Learning with Stochastic Stateful Policies, was accepted at the International Conference on Learning Representations (ICLR) 2024! We introduce a novel training approach for stateful policies, decomposing them into a stochastic internal state kernel and a stateless
Introducing the first imitation learning benchmark tailored towards locomotion. This benchmark comes with many different environments and motion capture dataset facilitating research in locomotion. We are happy to announce that we will present this work at the robot learning workshop
Happy to announce that our work on Least Squares Inverse Q-Learning got accepted to the European Workshop on Reinforcement Learning.
Our Paper, LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning was accepted at ICLR! We achieve fast and stable inverse reinforcement learning by using a squared reward regularizer on a mixture distribution between the expert and the policy distribution
I am honoured and pleased to receive the “Robotic Talents Award 2021” for my Master’s thesis “Comparing Reinforcement Learning Algorithms and Evolution Strategies on Robotic Manipulation Tasks”. This award was granted by the Ministry of Economic Affairs, Labour, and Digitalization
Great news! I will join the Intelligent Autonomous Systems (IAS) group at TU Darmstadt for my PhD at the beginning of November! Future news on my work will be provided here (and probably on this website as well).
I am happy to announce that our paper “Redundancy Resolution as Action Bias in Policy Search” was accept at the Conference on Robot Learning (CoRL2021)! Checkout our project website.
I have published a new blog showing my latest effort of training a position/pose estimator based purely on simulated data. Therefore, I have extended an approach considered as domain randomization. You can find the blog here. Check it out and
I have uploaded a new video showing how to use redundancy resolution in different policy search methods – including reinforcement learning and evolutions strategies – to embed secondary objectives without any reward shaping. This approach is evaluated in simulation and
I have published a blog on Bayesian optimization. The aim is to provide a simple hands-on tutorial for learning rate optimization. The tutorial concentrates on a classification task using the K-MNIST dataset. Check it out!
My website is online! This website is meant to show all my latest projects and blogs. I will try to cover different fields in machine learning, yet with a focus on reinforcement learning. So, stay tuned for some cool content