Michael Lutter
Michael Lutter
Intelligent Autonomous Systems, TU Darmstadt
Bestätigte E-Mail-Adresse bei ias.tu-darmstadt.de - Startseite
Zitiert von
Zitiert von
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
M Lutter, C Ritter, J Peters
International Conference on Learning Representations (ICLR), 2019
Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems
M Lutter, K Listmann, J Peters
International Conference on Intelligent Robots and Systems (IROS), 2019
Online learning of an open-ended skill library for collaborative tasks
D Koert, S Trick, M Ewerton, M Lutter, J Peters
2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 1-9, 2018
HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints
M Lutter, B Belousov, K Listmann, D Clever, J Peters
Conference on Robot Learning (CoRL), 2019
Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning
M Lutter, J Silberbauer, J Watson, J Peters
International Conference on Robotics and Automation (ICRA), 2021
High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards
K Ploeger, M Lutter, J Peters
Conference on Robot Learning (CoRL), 2020
A Differentiable Newton Euler Algorithm for Multi-body Model Learning
M Lutter, J Silberbauer, J Watson, J Peters
ICML Workshop on Inductive Biases, Invariances and Generalization in RL, 2020
Incremental learning of an open-ended collaborative skill library
D Koert, S Trick, M Ewerton, M Lutter, J Peters
International Journal of Humanoid Robotics 17 (01), 2050001, 2020
Learning dynamics models for model predictive agents
M Lutter, L Hasenclever, A Byravan, G Dulac-Arnold, P Trochim, N Heess, ...
arXiv preprint arXiv:2109.14311, 2021
Robust Value Iteration for Continuous Control Tasks
M Lutter, S Mannor, J Peters, D Fox, A Garg
Robotics: Science and Systems (RSS), 2021
Value Iteration in Continuous Actions, States and Time
M Lutter, S Mannor, J Peters, D Fox, A Garg
International Conference on Machone Learning (ICML), 2021
Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models
M Lutter, J Peters
arXiv preprint arXiv:2110.01894, 2021
Continuous-Time Fitted Value Iteration for Robust Policies
M Lutter, B Belousov, S Mannor, D Fox, A Garg, J Peters
arXiv preprint arXiv:2110.01954, 2021
Building Skill Learning Systems for Robotics
M Lutter, D Clever, R Kirsten, K Listmann, J Peters
2021 IEEE 17th International Conference on Automation Science and …, 2021
Trajectory Optimization of Energy Consumption and Expected Service Life of a Robotic System
F Stuhlenmiller, D Clever, S Rinderknecht, M Lutter, J Peters
2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics …, 2021
Evaluating the Robustness of HJB Optimal Feedback Control
M Lutter, D Clever, B Belousov, K Listmann, J Peters
ISR 2020; 52th International Symposium on Robotics, 1-8, 2020
Differential Equations as a Model Prior for Deep Learning and its Applications in Robotics
M Lutter, J Peters
ICLR 2020 Workshop on Integration of Deep Neural Models and Differential …, 2020
Deep Optimal Control: Using the Euler-Lagrange Equation to learn an Optimal Feedback Control Law
M Lutter, J Peters
Multi-disciplinary Conference on Reinforcement Learning and Decision Making …, 2019
Searching for a Better Policy Architecture for the OpenAI Bipedal Walker Environment
R Galljamov, B Belousov, M Lutter
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–19