Publications (15)
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
Michael Lutter, Christian Ritter, Jan Peters
Deep learning has achieved astonishing results on many tasks with large amounts of data and generalization within the proximity of training data. For many important real-world appl…
HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints
Michael Lutter, Boris Belousov, Kim Listmann +2
Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learni…
Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models
Michael Lutter, Jan Peters
Deep learning has been widely used within learning algorithms for robotics. One disadvantage of deep networks is that these networks are black-box representations. Therefore, the l…
Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning
Michael Lutter, Johannes Silberbauer, Joe Watson +1
A limitation of model-based reinforcement learning (MBRL) is the exploitation of errors in the learned models. Black-box models can fit complex dynamics with high fidelity, but the…
A Differentiable Newton Euler Algorithm for Multi-body Model Learning
Michael Lutter, Johannes Silberbauer, Joe Watson +1
In this work, we examine a spectrum of hybrid model for the domain of multi-body robot dynamics. We motivate a computation graph architecture that embodies the Newton Euler equatio…
Diminishing Return of Value Expansion Methods
Daniel Palenicek, Michael Lutter, João Carvalho +3
Model-based reinforcement learning aims to increase sample efficiency, but the accuracy of dynamics models and the resulting compounding errors are often seen as key limitations. T…