Policy Learning of Motor Skills for Humanoid Robots

Información del proyecto

SKILLS4ROBOTS

Identificador del acuerdo de subvención: 640554

DOI

10.3030/640554

Proyecto cerrado

Fecha de la firma de la CE 27 Mayo 2015

Fecha de inicio 1 Julio 2015

Fecha de finalización 30 Junio 2021

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 405 572,50

Aportación de la UE

€ 1 405 572,50

Coordinado por

TECHNISCHE UNIVERSITAT DARMSTADT
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 .

Publicaciones

Peer reviewed articles (10)

Compatible natural gradient policy search

Autores: Pajarinen, J., Thai, H.L., Akrour, R., Peters, J., Neumann, G.
Publicado en: Machine Learning, 2019, ISSN 0885-6125
Editor: Kluwer Academic Publishers

Learning Intention Aware Online Adaptation of Movement Primitives

Autores: Koert, D., Pajarinen, J., Schotschneider, A., Trick, S., Rothkopf, C., Peters, J.
Publicado en: IEEE Robotics and Automation Letters (RA-L), 2019, ISSN 2377-3766
Editor: IEEE

Multi-Channel Interactive Reinforcement Learning for Sequential Tasks

Autores: D. Koert, M. Kircher, V. Salikutluk, C. D'Eramo, J. Peters
Publicado en: Frontiers in Robotics and AI Human-Robot Interaction, 2020, ISSN 2296-9144
Editor: Frontiers Media S.A.

Evolutionary training and abstraction yields algorithmic generalization of neural computers

Autores: D. Tanneberg,E. Rueckert, J. Peters
Publicado en: Nature Machine Intelligence, 2020, ISSN 2522-5839
Editor: Springer Nature

Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks

Autores: Tanneberg, D.; Peters, J.; Rueckert, E.
Publicado en: Neural Networks, 2019, ISSN 0893-6080
Editor: Pergamon Press Ltd.

Entropic Regularization of Markov Decision Processes

Autores: B. Belousov, J. Peters
Publicado en: Entropy, 2019, ISSN 1099-4300
Editor: Multidisciplinary Digital Publishing Institute (MDPI)

Learning movement primitive libraries through probabilistic segmentation

Autores: Rudolf Lioutikov, Gerhard Neumann, Guilherme Maeda, Jan Peters
Publicado en: The International Journal of Robotics Research, Edición 36/8, 2017, Página(s) 879-894, ISSN 0278-3649
Editor: SAGE Publications
DOI: 10.1177/0278364917713116

Assisting Movement Training and Execution with Visual and Haptic Feedback

Autores: Ewerton, M.; Rother, D.; Weimar, J.; Kollegger, G.; Wiemeyer, J.; Peters, J.; Maeda, G.
Publicado en: Frontiers in Neurorobotics, 2018, ISSN 1662-5218
Editor: Frontiers Research Foundation

SKID RAW: Skill Discovery from Raw Trajectories

Autores: Daniel Tanneberg, Kai Ploeger, Elmar Rueckert, Jan Peters
Publicado en: IEEE Robotics and Automation Letters, 2021, ISSN 2377-3766
Editor: IEEE Robotics and Automation Society

Incremental Learning of an Open-Ended Collaborative Skill Library

Autores: D. Koert, S. Trick, M. Ewerton, M. Lutter, J. Peters
Publicado en: International Journal of Humanoid Robotics (IJHR), 2020, ISSN 0219-8436
Editor: World Scientific Publishing Co

Conference proceedings (18)

Interactive Assemblies: Man-Machine Collaboration through Building Components for As-Built Digital Models

Autores: Wibranek B., Belousov B., Sadybakasov A., Tessmann O.
Publicado en: Computer-Aided Architectural Design Futures (CAAD Futures), 2019
Editor: Springer

Receding Horizon Curiosity

Autores: Schultheis M., Belousov B., Abdulsamad H., Peters J. (2019). . Download Article BibTeX Reference
Publicado en: Proceedings of the 3rd Conference on Robot Learning (CoRL), 2019
Editor: ML Research Press

Online Learning of an Open-Ended Skill Library for Collaborative Tasks

Autores: Koert D., Trick S., Ewerton M., Lutter M., Peters J.
Publicado en: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2018
Editor: IEEE

Projections for Approximate Policy Iteration Algorithms

Autores: Riad Akrour, Joni Pajarinen, Jan Peters, Gerhard Neumann
Publicado en: Proceedings of Machine Learning Research, 2019
Editor: MLR Press

High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards

Autores: Kai Ploeger, Michael Lutter, Jan Peters
Publicado en: Proceedings of the 4th Conference on Robot Learning (CoRL), 2021
Editor: MLR Press

Reinforcement Learning for Sequential Assembly of SL-Blocks: Self-Interlocking Combinatorial Design Based on Machine Learning

Autores: B. Wibranek, Y. Liu, N. Funk, B. Belousov, J. Peters, O. Tessmann
Publicado en: Proceedings of the 39th eCAADe Conference, 2021
Editor: CumInCAD

Building a Library of Tactile Skills Based on FingerVision

Autores: Belousov B., Sadybakasov A., Wibranek B., Veiga F., Tessmann O., Peters J.
Publicado en: Proceedings of the 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019
Editor: IEEE

Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction

Autores: Trick S., Koert D., Peters J., Rothkopf C.
Publicado en: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Editor: IEEE

Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning

Autores: Michael Lutter, Christian Ritter, Jan Peters
Publicado en: International Conference on Learning Representations (ICLR), Edición 2019, 2019
Editor: ICLR

Underactuated Waypoint Trajectory Optimization for Light Painting Photography

Autores: Eilers, C., Eschmann, J., Menzenbach, R., Belousov, B., Muratore, F., Peters, J.
Publicado en: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2020
Editor: IEEE

Demonstration based trajectory optimization for generalizable robot motions

Autores: Dorothea Koert, Guilherme Maeda, Rudolf Lioutikov, Gerhard Neumann, Jan Peters
Publicado en: 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016, Página(s) 515-522, ISBN 978-1-5090-4718-5
Editor: IEEE
DOI: 10.1109/humanoids.2016.7803324

Catching heuristics are optimal control policies

Autores: Belousov, B.; Neumann, G.; Rothkopf, C.A.; Peters, J.
Publicado en: Proceedings of the Karniel Thirteenth Computational Motor Control Workshop, 2017, Página(s) 1-15
Editor: Ben-Gurion University

Catching heuristics are optimal control policies

Autores: Belousov, B.; Neumann, G.; Rothkopf, C.; Peters, J.
Publicado en: Advances in Neural Information Processing Systems, Edición yearly, 2016
Editor: NIPS Foundation

State-Regularized Policy Search for Linearized Dynamical Systems

Autores: Abdulsamad, H.; Arenz, O.; Peters, J.; Neumann, G.
Publicado en: Proceedings of the International Conference on Automated Planning and Scheduling, 2017
Editor: ICAPS Foundation

Learning Coupled Forward-Inverse Models with Combined Prediction Errors

Autores: Koert D., Maeda G., Neumann G., Peters J.
Publicado en: Proceedings of the International Conference on Robotics and Automation (ICRA), 2018
Editor: IEEE

Entropic Risk Measure in Policy Search

Autores: Nass D., Belousov B., Peters J.
Publicado en: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Editor: IEEE

Information gathering in decentralized POMDPs by policy graph improvement

Autores: M. Lauri, J. Pajarinen, J. Peters
Publicado en: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020
Editor: Springer Nature

Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

Autores: D. Tanneberg, J. Peters, E. Rueckert
Publicado en: Proceedings of the Conference on Robot Learning (CoRL), 2017
Editor: MLResearchPress

Thesis and dissertations (8)

Inductive Biases for Machine Learning in Robotics and Control

Autores: M. Lutter
Publicado en: Ph.D. Thesis, TU Darmstadt, 2021
Editor: ULB

Understand-Compute-Adapt: Neural Networks for Intelligent Agents,

Autores: Tanneberg D.
Publicado en: Ph.D. Thesis, TU Darmstadt, 2020
Editor: ULB

Minimax and entropic proximal policy optimization

Autores: Y. Song
Publicado en: Master Thesis, TU Darmstadt, 2018
Editor: ULB

Parsing Motion and Composing Behavior for Semi-Autonomous Manipulation

Autores: R. Lioutikov
Publicado en: PhD Thesis, TU Darmstadt, 2018
Editor: ULB

Bidirectional Human-Robot Learning: Imitation and Skill Improvement

Autores: M. Ewerton
Publicado en: PhD Thesis, TU Darmstadt, 2019
Editor: ULB

Statistical Machine Learning for Stochastic Structured Systems

Autores: H. Abdulsamad
Publicado en: Ph.D. Thesis, TU Darmstadt, 2021
Editor: ULB

Generalization and Transferability in Reinforcement Learning

Autores: P. Klink
Publicado en: Master Thesis, TU Darmstadt, 2019
Editor: ULB

Reinforcement Learning with Sparse and Multiple Rewards

Autores: S. Parisi
Publicado en: PhD Thesis. TU Darmstadt, 2019
Editor: ULB

Other (1)

f-Divergence constrained policy improvement

Autores: Belousov, Boris; Peters, Jan
Publicado en: Edición 2, 2018
Editor: ArXiV