Policy Learning of Motor Skills for Humanoid Robots

Compatible natural gradient policy search

Auteurs: Pajarinen, J., Thai, H.L., Akrour, R., Peters, J., Neumann, G.
Publié dans: Machine Learning, 2019, ISSN 0885-6125
Éditeur: Kluwer Academic Publishers

Learning Intention Aware Online Adaptation of Movement Primitives

Auteurs: Koert, D., Pajarinen, J., Schotschneider, A., Trick, S., Rothkopf, C., Peters, J.
Publié dans: IEEE Robotics and Automation Letters (RA-L), 2019, ISSN 2377-3766
Éditeur: IEEE

Multi-Channel Interactive Reinforcement Learning for Sequential Tasks

Auteurs: D. Koert, M. Kircher, V. Salikutluk, C. D'Eramo, J. Peters
Publié dans: Frontiers in Robotics and AI Human-Robot Interaction, 2020, ISSN 2296-9144
Éditeur: Frontiers Media S.A.

Evolutionary training and abstraction yields algorithmic generalization of neural computers

Auteurs: D. Tanneberg,E. Rueckert, J. Peters
Publié dans: Nature Machine Intelligence, 2020, ISSN 2522-5839
Éditeur: Springer Nature

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

Auteurs: Tanneberg, D.; Peters, J.; Rueckert, E.
Publié dans: Neural Networks, 2019, ISSN 0893-6080
Éditeur: Pergamon Press Ltd.

Entropic Regularization of Markov Decision Processes

Auteurs: B. Belousov, J. Peters
Publié dans: Entropy, 2019, ISSN 1099-4300
Éditeur: Multidisciplinary Digital Publishing Institute (MDPI)

Learning movement primitive libraries through probabilistic segmentation

Auteurs: Rudolf Lioutikov, Gerhard Neumann, Guilherme Maeda, Jan Peters
Publié dans: The International Journal of Robotics Research, Numéro 36/8, 2017, Page(s) 879-894, ISSN 0278-3649
Éditeur: SAGE Publications
DOI: 10.1177/0278364917713116

Assisting Movement Training and Execution with Visual and Haptic Feedback

Auteurs: Ewerton, M.; Rother, D.; Weimar, J.; Kollegger, G.; Wiemeyer, J.; Peters, J.; Maeda, G.
Publié dans: Frontiers in Neurorobotics, 2018, ISSN 1662-5218
Éditeur: Frontiers Research Foundation

SKID RAW: Skill Discovery from Raw Trajectories

Auteurs: Daniel Tanneberg, Kai Ploeger, Elmar Rueckert, Jan Peters
Publié dans: IEEE Robotics and Automation Letters, 2021, ISSN 2377-3766
Éditeur: IEEE Robotics and Automation Society

Incremental Learning of an Open-Ended Collaborative Skill Library

Auteurs: D. Koert, S. Trick, M. Ewerton, M. Lutter, J. Peters
Publié dans: International Journal of Humanoid Robotics (IJHR), 2020, ISSN 0219-8436
Éditeur: World Scientific Publishing Co

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

Auteurs: Wibranek B., Belousov B., Sadybakasov A., Tessmann O.
Publié dans: Computer-Aided Architectural Design Futures (CAAD Futures), 2019
Éditeur: Springer

Receding Horizon Curiosity

Auteurs: Schultheis M., Belousov B., Abdulsamad H., Peters J. (2019). . Download Article BibTeX Reference
Publié dans: Proceedings of the 3rd Conference on Robot Learning (CoRL), 2019
Éditeur: ML Research Press

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

Auteurs: Koert D., Trick S., Ewerton M., Lutter M., Peters J.
Publié dans: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2018
Éditeur: IEEE

Projections for Approximate Policy Iteration Algorithms

Auteurs: Riad Akrour, Joni Pajarinen, Jan Peters, Gerhard Neumann
Publié dans: Proceedings of Machine Learning Research, 2019
Éditeur: MLR Press

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

Auteurs: Kai Ploeger, Michael Lutter, Jan Peters
Publié dans: Proceedings of the 4th Conference on Robot Learning (CoRL), 2021
Éditeur: MLR Press

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

Auteurs: B. Wibranek, Y. Liu, N. Funk, B. Belousov, J. Peters, O. Tessmann
Publié dans: Proceedings of the 39th eCAADe Conference, 2021
Éditeur: CumInCAD

Building a Library of Tactile Skills Based on FingerVision

Auteurs: Belousov B., Sadybakasov A., Wibranek B., Veiga F., Tessmann O., Peters J.
Publié dans: Proceedings of the 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019
Éditeur: IEEE

Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction

Auteurs: Trick S., Koert D., Peters J., Rothkopf C.
Publié dans: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Éditeur: IEEE

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

Auteurs: Michael Lutter, Christian Ritter, Jan Peters
Publié dans: International Conference on Learning Representations (ICLR), Numéro 2019, 2019
Éditeur: ICLR

Underactuated Waypoint Trajectory Optimization for Light Painting Photography

Auteurs: Eilers, C., Eschmann, J., Menzenbach, R., Belousov, B., Muratore, F., Peters, J.
Publié dans: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2020
Éditeur: IEEE

Demonstration based trajectory optimization for generalizable robot motions

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

Catching heuristics are optimal control policies

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

Catching heuristics are optimal control policies

Auteurs: Belousov, B.; Neumann, G.; Rothkopf, C.; Peters, J.
Publié dans: Advances in Neural Information Processing Systems, Numéro yearly, 2016
Éditeur: NIPS Foundation

State-Regularized Policy Search for Linearized Dynamical Systems

Auteurs: Abdulsamad, H.; Arenz, O.; Peters, J.; Neumann, G.
Publié dans: Proceedings of the International Conference on Automated Planning and Scheduling, 2017
Éditeur: ICAPS Foundation

Learning Coupled Forward-Inverse Models with Combined Prediction Errors

Auteurs: Koert D., Maeda G., Neumann G., Peters J.
Publié dans: Proceedings of the International Conference on Robotics and Automation (ICRA), 2018
Éditeur: IEEE

Entropic Risk Measure in Policy Search

Auteurs: Nass D., Belousov B., Peters J.
Publié dans: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Éditeur: IEEE

Information gathering in decentralized POMDPs by policy graph improvement

Auteurs: M. Lauri, J. Pajarinen, J. Peters
Publié dans: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020
Éditeur: Springer Nature

Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

Auteurs: D. Tanneberg, J. Peters, E. Rueckert
Publié dans: Proceedings of the Conference on Robot Learning (CoRL), 2017
Éditeur: MLResearchPress

Inductive Biases for Machine Learning in Robotics and Control

Auteurs: M. Lutter
Publié dans: Ph.D. Thesis, TU Darmstadt, 2021
Éditeur: ULB

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

Auteurs: Tanneberg D.
Publié dans: Ph.D. Thesis, TU Darmstadt, 2020
Éditeur: ULB

Minimax and entropic proximal policy optimization

Auteurs: Y. Song
Publié dans: Master Thesis, TU Darmstadt, 2018
Éditeur: ULB

Parsing Motion and Composing Behavior for Semi-Autonomous Manipulation

Auteurs: R. Lioutikov
Publié dans: PhD Thesis, TU Darmstadt, 2018
Éditeur: ULB

Bidirectional Human-Robot Learning: Imitation and Skill Improvement

Auteurs: M. Ewerton
Publié dans: PhD Thesis, TU Darmstadt, 2019
Éditeur: ULB

Statistical Machine Learning for Stochastic Structured Systems

Auteurs: H. Abdulsamad
Publié dans: Ph.D. Thesis, TU Darmstadt, 2021
Éditeur: ULB

Generalization and Transferability in Reinforcement Learning

Auteurs: P. Klink
Publié dans: Master Thesis, TU Darmstadt, 2019
Éditeur: ULB

Reinforcement Learning with Sparse and Multiple Rewards

Auteurs: S. Parisi
Publié dans: PhD Thesis. TU Darmstadt, 2019
Éditeur: ULB

f-Divergence constrained policy improvement

Auteurs: Belousov, Boris; Peters, Jan
Publié dans: Numéro 2, 2018
Éditeur: ArXiV

Publications

Partager cette page

Télécharger