Policy Learning of Motor Skills for Humanoid Robots

Project Information

SKILLS4ROBOTS

Grant agreement ID: 640554

DOI 10.3030/640554

Project closed

EC signature date 27 May 2015

Start date 1 July 2015

End date 30 June 2021

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost € 1 405 572,50

EU contribution € 1 405 572,50

Coordinated by

TECHNISCHE UNIVERSITAT DARMSTADT
Germany

Publications

Peer reviewed articles (10)

Compatible natural gradient policy search

Author(s): Pajarinen, J., Thai, H.L., Akrour, R., Peters, J., Neumann, G.
Published in: Machine Learning, 2019, ISSN 0885-6125
Publisher: Kluwer Academic Publishers

Learning Intention Aware Online Adaptation of Movement Primitives

Author(s): Koert, D., Pajarinen, J., Schotschneider, A., Trick, S., Rothkopf, C., Peters, J.
Published in: IEEE Robotics and Automation Letters (RA-L), 2019, ISSN 2377-3766
Publisher: IEEE

Multi-Channel Interactive Reinforcement Learning for Sequential Tasks

Author(s): D. Koert, M. Kircher, V. Salikutluk, C. D'Eramo, J. Peters
Published in: Frontiers in Robotics and AI Human-Robot Interaction, 2020, ISSN 2296-9144
Publisher: Frontiers Media S.A.

Evolutionary training and abstraction yields algorithmic generalization of neural computers

Author(s): D. Tanneberg,E. Rueckert, J. Peters
Published in: Nature Machine Intelligence, 2020, ISSN 2522-5839
Publisher: Springer Nature

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

Author(s): Tanneberg, D.; Peters, J.; Rueckert, E.
Published in: Neural Networks, 2019, ISSN 0893-6080
Publisher: Pergamon Press Ltd.

Entropic Regularization of Markov Decision Processes

Author(s): B. Belousov, J. Peters
Published in: Entropy, 2019, ISSN 1099-4300
Publisher: Multidisciplinary Digital Publishing Institute (MDPI)

Learning movement primitive libraries through probabilistic segmentation

Author(s): Rudolf Lioutikov, Gerhard Neumann, Guilherme Maeda, Jan Peters
Published in: The International Journal of Robotics Research, Issue 36/8, 2017, Page(s) 879-894, ISSN 0278-3649
Publisher: SAGE Publications
DOI: 10.1177/0278364917713116

Assisting Movement Training and Execution with Visual and Haptic Feedback

Author(s): Ewerton, M.; Rother, D.; Weimar, J.; Kollegger, G.; Wiemeyer, J.; Peters, J.; Maeda, G.
Published in: Frontiers in Neurorobotics, 2018, ISSN 1662-5218
Publisher: Frontiers Research Foundation

SKID RAW: Skill Discovery from Raw Trajectories

Author(s): Daniel Tanneberg, Kai Ploeger, Elmar Rueckert, Jan Peters
Published in: IEEE Robotics and Automation Letters, 2021, ISSN 2377-3766
Publisher: IEEE Robotics and Automation Society

Incremental Learning of an Open-Ended Collaborative Skill Library

Author(s): D. Koert, S. Trick, M. Ewerton, M. Lutter, J. Peters
Published in: International Journal of Humanoid Robotics (IJHR), 2020, ISSN 0219-8436
Publisher: World Scientific Publishing Co

Conference proceedings (18)

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

Author(s): Wibranek B., Belousov B., Sadybakasov A., Tessmann O.
Published in: Computer-Aided Architectural Design Futures (CAAD Futures), 2019
Publisher: Springer

Receding Horizon Curiosity

Author(s): Schultheis M., Belousov B., Abdulsamad H., Peters J. (2019). . Download Article BibTeX Reference
Published in: Proceedings of the 3rd Conference on Robot Learning (CoRL), 2019
Publisher: ML Research Press

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

Author(s): Koert D., Trick S., Ewerton M., Lutter M., Peters J.
Published in: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2018
Publisher: IEEE

Projections for Approximate Policy Iteration Algorithms

Author(s): Riad Akrour, Joni Pajarinen, Jan Peters, Gerhard Neumann
Published in: Proceedings of Machine Learning Research, 2019
Publisher: MLR Press

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

Author(s): Kai Ploeger, Michael Lutter, Jan Peters
Published in: Proceedings of the 4th Conference on Robot Learning (CoRL), 2021
Publisher: MLR Press

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

Author(s): B. Wibranek, Y. Liu, N. Funk, B. Belousov, J. Peters, O. Tessmann
Published in: Proceedings of the 39th eCAADe Conference, 2021
Publisher: CumInCAD

Building a Library of Tactile Skills Based on FingerVision

Author(s): Belousov B., Sadybakasov A., Wibranek B., Veiga F., Tessmann O., Peters J.
Published in: Proceedings of the 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019
Publisher: IEEE

Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction

Author(s): Trick S., Koert D., Peters J., Rothkopf C.
Published in: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Publisher: IEEE

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

Author(s): Michael Lutter, Christian Ritter, Jan Peters
Published in: International Conference on Learning Representations (ICLR), Issue 2019, 2019
Publisher: ICLR

Underactuated Waypoint Trajectory Optimization for Light Painting Photography

Author(s): Eilers, C., Eschmann, J., Menzenbach, R., Belousov, B., Muratore, F., Peters, J.
Published in: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2020
Publisher: IEEE

Demonstration based trajectory optimization for generalizable robot motions

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

Catching heuristics are optimal control policies

Author(s): Belousov, B.; Neumann, G.; Rothkopf, C.A.; Peters, J.
Published in: Proceedings of the Karniel Thirteenth Computational Motor Control Workshop, 2017, Page(s) 1-15
Publisher: Ben-Gurion University

Catching heuristics are optimal control policies

Author(s): Belousov, B.; Neumann, G.; Rothkopf, C.; Peters, J.
Published in: Advances in Neural Information Processing Systems, Issue yearly, 2016
Publisher: NIPS Foundation

State-Regularized Policy Search for Linearized Dynamical Systems

Author(s): Abdulsamad, H.; Arenz, O.; Peters, J.; Neumann, G.
Published in: Proceedings of the International Conference on Automated Planning and Scheduling, 2017
Publisher: ICAPS Foundation

Learning Coupled Forward-Inverse Models with Combined Prediction Errors

Author(s): Koert D., Maeda G., Neumann G., Peters J.
Published in: Proceedings of the International Conference on Robotics and Automation (ICRA), 2018
Publisher: IEEE

Entropic Risk Measure in Policy Search

Author(s): Nass D., Belousov B., Peters J.
Published in: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Publisher: IEEE

Information gathering in decentralized POMDPs by policy graph improvement

Author(s): M. Lauri, J. Pajarinen, J. Peters
Published in: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020
Publisher: Springer Nature

Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

Author(s): D. Tanneberg, J. Peters, E. Rueckert
Published in: Proceedings of the Conference on Robot Learning (CoRL), 2017
Publisher: MLResearchPress

Thesis and dissertations (8)

Inductive Biases for Machine Learning in Robotics and Control

Author(s): M. Lutter
Published in: Ph.D. Thesis, TU Darmstadt, 2021
Publisher: ULB

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

Author(s): Tanneberg D.
Published in: Ph.D. Thesis, TU Darmstadt, 2020
Publisher: ULB

Minimax and entropic proximal policy optimization

Author(s): Y. Song
Published in: Master Thesis, TU Darmstadt, 2018
Publisher: ULB

Parsing Motion and Composing Behavior for Semi-Autonomous Manipulation

Author(s): R. Lioutikov
Published in: PhD Thesis, TU Darmstadt, 2018
Publisher: ULB

Bidirectional Human-Robot Learning: Imitation and Skill Improvement

Author(s): M. Ewerton
Published in: PhD Thesis, TU Darmstadt, 2019
Publisher: ULB

Statistical Machine Learning for Stochastic Structured Systems

Author(s): H. Abdulsamad
Published in: Ph.D. Thesis, TU Darmstadt, 2021
Publisher: ULB

Generalization and Transferability in Reinforcement Learning

Author(s): P. Klink
Published in: Master Thesis, TU Darmstadt, 2019
Publisher: ULB

Reinforcement Learning with Sparse and Multiple Rewards

Author(s): S. Parisi
Published in: PhD Thesis. TU Darmstadt, 2019
Publisher: ULB

Other (1)

f-Divergence constrained policy improvement

Author(s): Belousov, Boris; Peters, Jan
Published in: Issue 2, 2018
Publisher: ArXiV