Model-based Reinforcement Learning for Versatile Robots in the Real World

Project Information

REAL-RL

Grant agreement ID: 101045454

DOI 10.3030/101045454

EC signature date 30 August 2022

Start date 1 January 2023

End date 31 December 2027

Funded under

• European Research Council (ERC)

Total cost € 1 998 500,00

EU contribution € 1 998 500,00

Coordinated by

EBERHARD KARLS UNIVERSITAET TUEBINGEN
Germany

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (12)

Efficient Learning of High Level Plans from Play

Author(s): Armengol Urpi, N. and Bagatella, M. and Hilliges, O. and Martius, G. and Coros, S.
Published in: IEEE, 2023
Publisher: IEEE
DOI: 10.1109/ICRA48891.2023.10161415

LPGD: A General Framework for Backpropagation through Embedded Optimization Layers

Author(s): Paulus, A. and Martius, G. and Musil, V.
Published in: ICML International Conference on Machine Learning, 2024
Publisher: PMLR

Learning with 3D rotations, a hitchhiker's guide to SO(3)

Author(s): Geist, Andreas Reé and Frey, Jonas and Zhobro, Mikel and Levina, Anna and Martius, Georg
Published in: ICML International Conference on Machine Learning, 2024
Publisher: PMLR

Bridging the Gap to Real-World Object-Centric Learning

Author(s): Seitzer, Maximilian and Horn, Max and Zadaianchuk, Andrii and Zietlow, Dominik and Xiao, Tianjun and Simon-Gabriel, Carl-Johann and He, Tong and Zhang, Zheng and Schölkopf, Bernhard and Brox, Thomas and Locatello, Francesco
Published in: ICLR International Conference on Learning Representations, 2023
Publisher: ICLR

Backpropagation through Combinatorial Algorithms: Identity with Projection Works

Author(s): Sahoo, Subham and Paulus, Anselm and Vlastelica, Marin and Musil, Vit and Kuleshov, Volodymyr and Martius, Georg
Published in: ICLR International Conference on Learning Representations, 2023
Publisher: ICLR

Goal-conditioned Offline Planning from Curious Exploration

Author(s): Bagatella, Marco and Martius, Georg
Published in: NeurIPS/ Advances in Information Processing, 2023
Publisher: Curran Associates

Learning Diverse Skills for Local Navigation under Multi-constraint Optimality

Author(s): Jin Cheng, Marin Vlastelica, Pavel Kolev, Chenhao Li, Georg Martius
Published in: 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024
Publisher: IEEE
DOI: 10.1109/ICRA57147.2024.10611629

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

Author(s): Zadaianchuk, Andrii and Seitzer, Maximilian and Martius, Georg
Published in: NeurIPS/ Advances in Information Processing, 2023
Publisher: Curran Associates

Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning

Author(s): Eberhard, Onno and Hollenstein, Jakob and Pinneri, Cristina and Martius, Georg
Published in: ICLR International Conference on Learning Representations, 2023
Publisher: ICLR

Causal Action Influence Aware Counterfactual Data Augmentation

Author(s): Urpi, N. A. and Bagatella, M. and Vlastelica, M. and Martius, G.
Published in: International Conference on Machine Learning (ICML), 2024
Publisher: PMLR

Benchmarking Offline Reinforcement Learning on Real-Robot Hardware

Author(s): Gürtler, Nico and Blaes, Sebastian and Kolev, Pavel and Widmaier, Felix and Wüthrich, Manuel and Bauer, Stefan and Schölkopf, Bernhard and Martius, Georg
Published in: ICLR International Conference on Learning Representations, 2023
Publisher: ICLR

Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics

Author(s): Gumbsch, Christian and Sajid, Noor and Martius, Georg and Butz, Martin V.
Published in: ICLR International Conference on Learning Representations, 2024
Publisher: ICLR