74 citations · 155 across the 16 of their papers we have counts for
16 papers
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
Marvin Alles, Philip Becker-Ehmck, Patrick van der Smagt +1
In offline reinforcement learning, a policy is learned using a static dataset in the absence of costly feedback from the environment. In contrast to the online setting, only using…
Adapting Deep Variational Bayes Filter for Enhanced Confidence Estimation in Finite Element Method Integrated Networks (FEMIN)
Simon Thel, Lars Greve, Maximilian Karl +1
The Finite Element Method (FEM) is a widely used technique for simulating crash scenarios with high accuracy and reliability. To reduce the significant computational costs associat…
Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt +1
Pretraining and finetuning models has become increasingly popular in decision-making. But there are still serious impediments in Imitation Learning from Observation (ILfO) with pre…
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt +1
Unlike most reinforcement learning agents which require an unrealistic amount of environment interactions to learn a new behaviour, humans excel at learning quickly by merely obser…
On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer
Elie Aljalbout, Felix Frank, Maximilian Karl +1
We study the choice of action space in robot manipulation learning and sim-to-real transfer. We define metrics that assess the performance, and examine the emerging properties in t…
CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces
Elie Aljalbout, Maximilian Karl, Patrick van der Smagt
Multi-robot manipulation tasks involve various control entities that can be separated into dynamically independent parts. A typical example of such real-world tasks is dual-arm man…
Learning to Fly via Deep Model-Based Reinforcement Learning
Philip Becker-Ehmck, Maximilian Karl, Jan Peters +1
Learning to control robots without requiring engineered models has been a long-term goal, promising diverse and novel applications. Yet, reinforcement learning has only achieved li…
Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
Neha Das, Maximilian Karl, Philip Becker-Ehmck +1
Learning a model of dynamics from high-dimensional images can be a core ingredient for success in many applications across different domains, especially in sequential decision maki…
Unsupervised Real-Time Control through Variational Empowerment
Maximilian Karl, Maximilian Soelch, Philip Becker-Ehmck +3
We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control.…
Variational Inference with Hamiltonian Monte Carlo
Christopher Wolf, Maximilian Karl, Patrick van der Smagt
Variational inference lies at the core of many state-of-the-art algorithms. To improve the approximation of the posterior beyond parametric families, it was proposed to include MCM…
Unsupervised preprocessing for Tactile Data
Maximilian Karl, Justin Bayer, Patrick van der Smagt
Tactile information is important for gripping, stable grasp, and in-hand manipulation, yet the complexity of tactile data prevents widespread use of such sensors. We make use of an…
ML-based tactile sensor calibration: A universal approach
Maximilian Karl, Artur Lohrer, Dhananjay Shah +5
We study the responses of two tactile sensors, the fingertip sensor from the iCub and the BioTac under different external stimuli. The question of interest is to which degree both…
Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
Maximilian Karl, Maximilian Soelch, Justin Bayer +1
We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models. Leveraging recent advances in…
Efficient Empowerment
Maximilian Karl, Justin Bayer, Patrick van der Smagt
Empowerment quantifies the influence an agent has on its environment. This is formally achieved by the maximum of the expected KL-divergence between the distribution of the success…
Fast Adaptive Weight Noise
Justin Bayer, Maximilian Karl, Daniela Korhammer +1
Marginalising out uncertain quantities within the internal representations or parameters of neural networks is of central importance for a wide range of learning techniques, such a…
Improving approximate RPCA with a k-sparsity prior
Maximilian Karl, Christian Osendorfer
A process centric view of robust PCA (RPCA) allows its fast approximate implementation based on a special form o a deep neural network with weights shared across all layers. Howeve…