Efficient Off-Policy Learning for High-Dimensional Action Spaces
Fabian Otto, Philipp Becker, Vien Anh Ngo, Gerhard NeumannInternational Conference for Learning Representations (ICLR)
- Model-free 5
- Trust Regions 5
- Movement Primitives 4
- Review 1
- Representation Learning 1
- Vision-Language-Action Models 1
- Imitation Learning 1
Model-free
International Conference for Learning Representations (ICLR)
MP3: Movement Primitive-Based (Re-)Planning Policy
Fabian Otto, Hongyi Zhou, Onur Celik, Ge Li, Rudolf Lioutikov, Gerhard NeumannCoRL Workshop on Learning Effective Abstractions for Planning (LEAP)
Deep Black-Box Reinforcement Learning with Movement Primitives
Fabian Otto, Onur Celik, Hongyi Zhou, Hanna Ziesche, Ngo Anh Vien, Gerhard NeumannConference on Robot Learning (CoRL)
Differentiable Trust Region Layers for Deep Reinforcement Learning
Fabian Otto, Philipp Becker, Ngo Anh Vien, Hanna Carolin Ziesche, Gerhard NeumannInternational Conference for Learning Representations (ICLR)
Model-free Deep Reinforcement Learning – Algorithms and Applications
Fabian OttoReinforcement Learning Algorithms: Analysis and Applications. Studies in Computational Intelligence, vol 883.
Trust Regions
Efficient Off-Policy Learning for High-Dimensional Action Spaces
Fabian Otto, Philipp Becker, Vien Anh Ngo, Gerhard NeumannInternational Conference for Learning Representations (ICLR)
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
Ge Li, Hongyi Zhou, Dominik Roth, Serges Thilges, Fabian Otto, Rudolf Lioutikov, Gerhard NeumannInternational Conference for Learning Representations (ICLR)
MP3: Movement Primitive-Based (Re-)Planning Policy
Fabian Otto, Hongyi Zhou, Onur Celik, Ge Li, Rudolf Lioutikov, Gerhard NeumannCoRL Workshop on Learning Effective Abstractions for Planning (LEAP)
Deep Black-Box Reinforcement Learning with Movement Primitives
Fabian Otto, Onur Celik, Hongyi Zhou, Hanna Ziesche, Ngo Anh Vien, Gerhard NeumannConference on Robot Learning (CoRL)
Differentiable Trust Region Layers for Deep Reinforcement Learning
Fabian Otto, Philipp Becker, Ngo Anh Vien, Hanna Carolin Ziesche, Gerhard NeumannInternational Conference for Learning Representations (ICLR)
Movement Primitives
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
Ge Li, Hongyi Zhou, Dominik Roth, Serges Thilges, Fabian Otto, Rudolf Lioutikov, Gerhard NeumannInternational Conference for Learning Representations (ICLR)
MP3: Movement Primitive-Based (Re-)Planning Policy
Fabian Otto, Hongyi Zhou, Onur Celik, Ge Li, Rudolf Lioutikov, Gerhard NeumannCoRL Workshop on Learning Effective Abstractions for Planning (LEAP)
ProDMP: A Unified Perspective on Dynamic and Probabilistic Movement Primitives
Ge Li, Zeqi Jin, Michael Volpp, Fabian Otto, Rudolf Lioutikov, Gerhard NeumannIEEE Robotics and Automation Letters (RA-L)
International Conference on Intelligent Robots and Systems (IROS)
Deep Black-Box Reinforcement Learning with Movement Primitives
Fabian Otto, Onur Celik, Hongyi Zhou, Hanna Ziesche, Ngo Anh Vien, Gerhard NeumannConference on Robot Learning (CoRL)
Review
Model-free Deep Reinforcement Learning – Algorithms and Applications
Fabian OttoReinforcement Learning Algorithms: Analysis and Applications. Studies in Computational Intelligence, vol 883.
Representation Learning
Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL
Philipp Becker, Sebastian Mossburger, Fabian Otto, Gerhard NeumannReinforcement Learning Conference (RLC)
Vision-Language-Action Models
FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
Moritz Reuss, Hongyi Zhou, Marcel Rühle, Ömer Erdinç Yağmurlu, Fabian Otto, Rudolf LioutikovICLR Robot Learning Workshop - Towards Robots with Human-Level Abilities
Imitation Learning
FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
Moritz Reuss, Hongyi Zhou, Marcel Rühle, Ömer Erdinç Yağmurlu, Fabian Otto, Rudolf LioutikovICLR Robot Learning Workshop - Towards Robots with Human-Level Abilities