Michael Lutter

31 papers A* 3A 1Misc 2Journal 18Unranked 5

Year	Rank	Type	Title / Venue / Authors
2024	J	`jnl`	Diminishing Return of Value Expansion Methods. CoRR Daniel Palenicek, Michael Lutter, João Carvalho, Daniel Dennert, Faran Ahmad, Jan Peters
2023	J	`jnl`	Combining physics and deep learning to learn continuous-time dynamics models. Int. J. Robotics Res. Michael Lutter, Jan Peters
2023	J	`jnl`	Continuous-Time Fitted Value Iteration for Robust Policies. IEEE Trans. Pattern Anal. Mach. Intell. Michael Lutter, Boris Belousov, Shie Mannor, Dieter Fox, Animesh Garg, Jan Peters
2023	A*	`conf`	Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning. ICLR Daniel Palenicek, Michael Lutter, Joao Carvalho, Jan Peters
2023	J	`jnl`	Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning. CoRR Daniel Palenicek, Michael Lutter, Joao Carvalho, Jan Peters
2023	—	`book`	Inductive Biases in Machine Learning for Robotics and Control Michael Lutter
2022	J	`jnl`	Revisiting Model-based Value Expansion. CoRR Daniel Palenicek, Michael Lutter, Jan Peters
2021	J	`jnl`	A Differentiable Newton-Euler Algorithm for Real-World Robotics. CoRR Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters
2021	—	`conf`	Building Skill Learning Systems for Robotics. CASE Michael Lutter, Debora Clever, René Kirsten, Kim Listmann, Jan Peters
2021	J	`jnl`	Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models. CoRR Michael Lutter, Jan Peters
2021	J	`jnl`	Continuous-Time Fitted Value Iteration for Robust Policies. CoRR Michael Lutter, Boris Belousov, Shie Mannor, Dieter Fox, Animesh Garg, Jan Peters
2021	A*	`conf`	Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning. ICRA Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters
2021	—	`—`	Inductive Biases in Machine Learning for Robotics and Control Michael Lutter
2021	J	`jnl`	Learning Dynamics Models for Model Predictive Agents. CoRR Michael Lutter, Leonard Hasenclever, Arunkumar Byravan, Gabriel Dulac-Arnold, Piotr Trochim, Nicolas Heess, Josh Merel, Yuval Tassa
2021	—	`conf`	Robust Value Iteration for Continuous Control Tasks. Robotics: Science and Systems Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg
2021	J	`jnl`	Robust Value Iteration for Continuous Control Tasks. CoRR Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg
2021	—	`conf`	Trajectory Optimization of Energy Consumption and Expected Service Life of a Robotic System. AIM Florian Stuhlenmiller, Debora Clever, Stephan Rinderknecht, Michael Lutter, Jan Peters
2021	A*	`conf`	Value Iteration in Continuous Actions, States and Time. ICML Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg
2021	J	`jnl`	Value Iteration in Continuous Actions, States and Time. CoRR Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg
2020	J	`jnl`	A Differentiable Newton Euler Algorithm for Multi-body Model Learning. CoRR Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters
2020	J	`jnl`	Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning. CoRR Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters
2020	Misc	`conf`	High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards. CoRL Kai Ploeger, Michael Lutter, Jan Peters
2020	J	`jnl`	High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards. CoRR Kai Ploeger, Michael Lutter, Jan Peters
2020	J	`jnl`	Incremental Learning of an Open-Ended Collaborative Skill Library. Int. J. Humanoid Robotics Dorothea Koert, Susanne Trick, Marco Ewerton, Michael Lutter, Jan Peters
2019	A	`conf`	Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems. IROS Michael Lutter, Kim Listmann, Jan Peters
2019	J	`jnl`	Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems. CoRR Michael Lutter, Kim Listmann, Jan Peters
2019	—	`conf`	Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning. ICLR (Poster) Michael Lutter, Christian Ritter, Jan Peters
2019	J	`jnl`	Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning. CoRR Michael Lutter, Christian Ritter, Jan Peters
2019	Misc	`conf`	HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints. CoRL Michael Lutter, Boris Belousov, Kim Listmann, Debora Clever, Jan Peters
2019	J	`jnl`	HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints. CoRR Michael Lutter, Boris Belousov, Kim Listmann, Debora Clever, Jan Peters
2018	—	`conf`	Online Learning of an Open-Ended Skill Library for Collaborative Tasks. Humanoids Dorothea Koert, Susanne Trick, Marco Ewerton, Michael Lutter, Jan Peters