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

Información del proyecto

REAL-RL

Identificador del acuerdo de subvención: 101045454

DOI

10.3030/101045454

Fecha de la firma de la CE 30 Agosto 2022

Fecha de inicio 1 Enero 2023

Fecha de finalización 31 Diciembre 2027

Financiado con arreglo a

• European Research Council (ERC)

Coste total

€ 1 998 500,00

Aportación de la UE

€ 1 998 500,00

Coordinado por

EBERHARD KARLS UNIVERSITAET TUEBINGEN
Germany

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Data Management Plan (1)

Data Management Plan

Publicaciones

Conference proceedings (14)

Efficient Learning of High Level Plans from Play

Autores: Armengol Urpi, N. and Bagatella, M. and Hilliges, O. and Martius, G. and Coros, S.
Publicado en: IEEE, 2023
Editor: IEEE
DOI: 10.1109/ICRA48891.2023.10161415

LPGD: A General Framework for Backpropagation through Embedded Optimization Layers

Autores: Paulus, A. and Martius, G. and Musil, V.
Publicado en: ICML International Conference on Machine Learning, 2024
Editor: PMLR

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

Autores: Geist, Andreas Reé and Frey, Jonas and Zhobro, Mikel and Levina, Anna and Martius, Georg
Publicado en: ICML International Conference on Machine Learning, 2024
Editor: PMLR

Bridging the Gap to Real-World Object-Centric Learning

Autores: 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
Publicado en: ICLR International Conference on Learning Representations, 2023
Editor: ICLR

Backpropagation through Combinatorial Algorithms: Identity with Projection Works

Autores: Sahoo, Subham and Paulus, Anselm and Vlastelica, Marin and Musil, Vit and Kuleshov, Volodymyr and Martius, Georg
Publicado en: ICLR International Conference on Learning Representations, 2023
Editor: ICLR

Goal-conditioned Offline Planning from Curious Exploration

Autores: Bagatella, Marco and Martius, Georg
Publicado en: NeurIPS/ Advances in Information Processing, 2023
Editor: Curran Associates

Learning Diverse Skills for Local Navigation under Multi-constraint Optimality

Autores: Jin Cheng, Marin Vlastelica, Pavel Kolev, Chenhao Li, Georg Martius
Publicado en: 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024
Editor: IEEE
DOI: 10.1109/ICRA57147.2024.10611629

Temporally Consistent Object-Centric Learning by Contrasting Slots

Autores: Manasyan, Anna and Seitzer, Maximilian and Radovic, Filip and Martius, Georg and Zadaianchuk, Andrii
Publicado en: CVPR: Conference on Computer Vision and Pattern Recognition, 2025
Editor: IEEE

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

Autores: Zadaianchuk, Andrii and Seitzer, Maximilian and Martius, Georg
Publicado en: NeurIPS/ Advances in Information Processing, 2023
Editor: Curran Associates

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

Autores: Eberhard, Onno and Hollenstein, Jakob and Pinneri, Cristina and Martius, Georg
Publicado en: ICLR International Conference on Learning Representations, 2023
Editor: ICLR

Causal Action Influence Aware Counterfactual Data Augmentation

Autores: Urpi, N. A. and Bagatella, M. and Vlastelica, M. and Martius, G.
Publicado en: International Conference on Machine Learning (ICML), 2024
Editor: PMLR

On the Transfer of Object-Centric Representation Learning

Autores: Didolkar, A. R. and Zadaianchuk, A. and Goyal, A. and Mozer, M. C. and Bengio, Y. and Martius*, G. and Seitzer*, M.
Publicado en: ICLR International Conference on Learning Representations, 2025
Editor: PMLR

Benchmarking Offline Reinforcement Learning on Real-Robot Hardware

Autores: Gürtler, Nico and Blaes, Sebastian and Kolev, Pavel and Widmaier, Felix and Wüthrich, Manuel and Bauer, Stefan and Schölkopf, Bernhard and Martius, Georg
Publicado en: ICLR International Conference on Learning Representations, 2023
Editor: ICLR

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

Autores: Gumbsch, Christian and Sajid, Noor and Martius, Georg and Butz, Martin V.
Publicado en: ICLR International Conference on Learning Representations, 2024
Editor: ICLR

Peer reviewed articles (1)

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies

Autores: Chen, Jiaqi and Shi, Ji and Sancaktar, Cansu and Frey, Jonas and Martius, Georg
Publicado en: Reinforcement Learning Journal, 2025, ISSN 2996-8577
Editor: RLJ
DOI: 10.48550/arXiv.2509.05735