BibTeX

You can download this complete bibtex reference list as all-ias-publications.bib.

@article{Lutter_SITR_submitted,
  author =		 "Lutter, M. and  Silberbauer, J. and  Watson, J. and  Peters, J.",
  year =		 "submitted",
  title =		 "A Differentiable Newton-Euler Algorithm for Real-World Robotics",
  booktitle =		 "Submitted to the IEEE Transaction of Robotics (T-Ro)",
  crossref =		 "p11472"
}

@article{2202,
  author =		 "Dam, T. and  D'Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "submitted",
  title =		 "A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search",
  booktitle =		 "Submitted to the Journal of Artificial Intelligence Research (JAIR)",
  URL =			 "https://arxiv.org/pdf/2202.07071",
  crossref =		 "p11490"
}

@article{230914091,
  author =		 "Klink, P. and  D'Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "submitted",
  title =		 "On the Benefit of Optimal Transport for Curriculum Reinforcement Learning",
  booktitle =		 "Submitted to the IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://arxiv.org/pdf/2309.14091.pdf",
  crossref =		 "p11599"
}

@article{230908256,
  author =		 "Look, A. and  Rakitsch, B. and  Kandemir, M. and  Peters, J.",
  year =		 "submitted",
  title =		 "Sampling-Free Probabilistic Deep State-Space Models",
  booktitle =		 "Submitted to Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://arxiv.org/pdf/2309.08256.pdf",
  crossref =		 "p11657"
}

@article{230914096,
  author =		 "Klink, P. and  Wolf, F. and  Ploeger, K. and  Peter, J. and  Pajarinen, J.",
  year =		 "submitted",
  title =		 "Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning",
  booktitle =		 "Submitted to the IEEE Transactions on Robotics (T-Ro)",
  URL =			 "https://arxiv.org/pdf/2309.14096.pdf",
  crossref =		 "p11666"
}

@article{evetac_paper,
  author =		 "Funk, N. and  Helmut, E. and  Chalvatzaki, G. and  Calandra, R. and  Peters, J.",
  year =		 "submitted",
  title =		 "Evetac: An Event-based Optical Tactile Sensor for Robotic Manipulation",
  booktitle =		 "Submitted to the IEEE Transactions on Robotics (T-Ro)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/NiklasFunk/evetac_paper.pdf",
  crossref =		 "p11709"
}

@article{2311,
  author =		 "Prasad, V. and  Heitlinger, L and  Koert, D. and  Stock-Homburg, R. and  Peters, J. and  Chalvatzaki, G.",
  year =		 "submitted",
  title =		 "Learning Multimodal Latent Dynamics for Human-Robot Interaction",
  booktitle =		 "Submitted to the IEEE Transaction of Robotics (T-RO)",
  URL =			 "https://arxiv.org/abs/2311.16380",
  crossref =		 "p11721"
}

@article{Prasad_SIRAL_submitted,
  author =		 "Prasad, V. and  Kshirsagar, A and  Koert, D. and  Stock-Homburg, R. and  Peters, J. and  Chalvatzaki, G.",
  year =		 "submitted",
  title =		 "MoVEInt: Mixture of Variational Experts for Learning Human-Robot Interactions from Demonstrations",
  booktitle =		 "Submitted to the IEEE Robotics and Automation Letters (RA-L)",
  crossref =		 "p11722"
}

@article{Establishment_of_Line_of_Sight_Optical_Links,
  author =		 "Weng, Y. and  Matsuda, T. and  Sekimoria, Y. and  Pajarinen, J. and  Peters, J. and  Maki, T.",
  year =		 "in press",
  title =		 "Establishment of Line-of-Sight Optical Links Between Autonomous Underwater Vehicles: Field Experiment and Performance Validation",
  booktitle =		 "Applied Ocean Research",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Research/Overview/Establishment_of_Line_of_Sight_Optical_Links.pdf",
  crossref =		 "p11554"
}

@article{211106211,
  author =		 "Abdulsamad, H. and  Peters, J.",
  year =		 "in press",
  title =		 "Model-Based Reinforcement Learning via Stochastic Hybrid Models",
  booktitle =		 "IEEE Open Journal of Control Systems, Special Section: Intersection of Machine Learning with Control",
  URL =			 "https://arxiv.org/pdf/2111.06211.pdf",
  crossref =		 "p11600"
}

@article{221116110,
  author =		 "Flynn, H. and  Reeb, D. and  Kandemir, M. and  Peters, J.",
  year =		 "in press",
  title =		 "PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://arxiv.org/pdf/2211.16110.pdf",
  crossref =		 "p11626"
}

@article{221101120,
  author =		 "Abdulsamad, H. and  Nickl, P. and  Klink, P. and  Peters, J.",
  year =		 "in press",
  title =		 "Variational Hierarchical Mixtures for Probabilistic Learning of Inverse Dynamics",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://arxiv.org/pdf/2211.01120.pdf",
  crossref =		 "p11649"
}

@article{230104330,
  author =		 "Kicki, P. and  Liu, P. and  Tateo, D. and  Bou Ammar, H. and  Walas, K. and  Skrzypczynski, P. and  Peters, J.",
  year =		 "2024",
  title =		 "Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks",
  booktitle =		 "IEEE Transactions on Robotics (T-Ro), and Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://arxiv.org/pdf/2301.04330.pdf",
  pages =		 "277-297",
  crossref =		 "p11679"
}

@inproceedings{pdfidPczQtTsTIX,
  author =		 "Bhatt, A. and  Palenicek, D. and  Belousov, B. and  Argus, M. and  Amiranashvili, A. and  Brox, T. and  Peters, J.",
  year =		 "2024",
  title =		 "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "https://openreview.net/pdf?id=PczQtTsTIX",
  crossref =		 "p11689"
}

@inproceedings{231209950,
  author =		 "Derstroff, C. and  Brugger, J. and  Cerrato, M. and  Peters, J. and  Kramer, S.",
  year =		 "2024",
  title =		 "Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations",
  booktitle =		 "Proceedings of the National Conference on Artificial Intelligence (AAAI)",
  URL =			 "https://arxiv.org/pdf/2312.09950.pdf",
  crossref =		 "p11703"
}

@inproceedings{231212869,
  author =		 "Vincent, T. and  Metelli, A. and  Belousov, B. and  Peters, J. and  Restelli, M. and  D'Eramo, C.",
  year =		 "2024",
  title =		 "Parameterized Projected Bellman Operator",
  booktitle =		 "Proceedings of the National Conference on Artificial Intelligence (AAAI)",
  URL =			 "https://arxiv.org/pdf/2312.12869.pdf",
  crossref =		 "p11704"
}

@inproceedings{231101885,
  author =		 "Tiboni, G. and  Klink, P. and  Peters, J. and  Tommasi, T. and  D'Eramo, C. and  Chalvatzaki, G.",
  year =		 "2024",
  title =		 "Domain Randomization via Entropy Maximization",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "https://arxiv.org/pdf/2311.01885.pdf",
  crossref =		 "p11714"
}

@inproceedings{240214548,
  author =		 "Hahne, F. and  Prasad V. and  Kshirsagar A. and  Koert D. and  Stock-Homburg R. M. and  Peters J. and  Chalvatzaki G.",
  year =		 "2024",
  title =		 "Transition State Clustering for Interaction Segmentation and Learning",
  booktitle =		 "ACM/IEEE International Conference on Human Robot Interaction (HRI), Late Breaking Report",
  URL =			 "https://arxiv.org/pdf/2402.14548.pdf",
  crossref =		 "p11711"
}

@inproceedings{240214525,
  author =		 "Goeksu, Y. and  Almeida-Correia, A. and  Prasad, V. and  Kshirsagar, A. and  Koert, D. and  Peters, J. and  Chalvatzaki, G.",
  year =		 "2024",
  title =		 "Kinematically Constrained Human-like Bimanual Robot-to-Human Handovers",
  booktitle =		 "ACM/IEEE International Conference on Human Robot Interaction (HRI), Late Breaking Report",
  URL =			 "https://arxiv.org/pdf/2402.14525.pdf",
  crossref =		 "p11713"
}

@inproceedings{231111385,
  author =		 "Hendawy, A. and  Peters, J. and  D'Eramo, C.",
  year =		 "2024",
  title =		 "Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "https://arxiv.org/pdf/2311.11385.pdf",
  crossref =		 "p11715"
}

@inproceedings{231101642,
  author =		 "Reddi, A. and  Toelle, M. and  Peters, J. and  Chalvatzaki, G. and  D'Eramo, C.",
  year =		 "2024",
  title =		 "Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "https://arxiv.org/pdf/2311.01642.pdf",
  crossref =		 "p11717"
}

@inproceedings{231104082,
  author =		 "Al-Hafez, F. and  Zhao, G. and  Peters, J. and  Tateo, D.",
  year =		 "2024",
  title =		 "Time-Efficient Reinforcement Learning with Stochastic Stateful Policies",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  key =			 "reinforcement learning, imitation, stateful policies",
  URL =			 "https://arxiv.org/pdf/2311.04082.pdf",
  crossref =		 "p11718"
}

@inproceedings{Scherf_HRI2024,
  author =		 "Scherf, L. and  Gasche, L. A. and  Chemangui, E. and  Koert, D.",
  year =		 "2024",
  title =		 "Are You Sure? - Multi-Modal Human Decision Uncertainty Detection in Human-Robot Interaction",
  booktitle =		 "2024 ACM/IEEE International Conference on Human-Robot Interaction (HRI ’24)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/LisaScherf/Scherf_HRI2024.pdf",
  crossref =		 "p11730"
}

@inproceedings{boehm24_tart,
  author =		 "Boehm, A. and  Schneider, T. and  Belousov, B. and  Kshirsagar, A. and  Lin, L. and  Doerschner, K. and  Drewing, K. and  Rothkopf, C.A. and  Peters, J.",
  year =		 "2024",
  title =		 "What Matters for Active Texture Recognition With Vision-Based Tactile Sensors",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/boehm24_tart.pdf",
  crossref =		 "p11731"
}

@inproceedings{boehm24_tart,
  author =		 "Boehm, A. and  Schneider, T. and  Belousov, B. and  Kshirsagar, A. and  Lin, L and  Doerschner, K. and  Drewing, K. and  Rothkopf, C. and  Peters, J.",
  year =		 "2024",
  title =		 "What Matters for Active Texture Recognition with Vision-Based Tactile Sensors",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/boehm24_tart.pdf",
  crossref =		 "p11733"
}

@inproceedings{231107245,
  author =		 "Lach, L. and  Haschke, R. and  Tateo, D. and  Peters, J. and  Ritter, H. and  Sol, J. and  Torras, C.",
  year =		 "2024",
  title =		 "Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://arxiv.org/pdf/2311.07245.pdf",
  crossref =		 "p11734"
}

@article{190403665,
  author =		 "Buechler, D. and  Calandra, R. and  Peters, J.",
  year =		 "2023",
  title =		 "Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots",
  booktitle =		 "Robotics and Autonomous Systems",
  URL =			 "https://arxiv.org/pdf/1904.03665.pdf",
  number =		 "104230",
  crossref =		 "p11543"
}

@inproceedings{Toelle_CWLRLLG_2023,
  author =		 "Toelle, M. and  Belousov, B. and  Peters, J.",
  year =		 "2023",
  title =		 "A Unifying Perspective on Language-Based Task Representations for Robot Control",
  booktitle =		 "CoRL Workshop on Language and Robot Learning: Language as Grounding",
  key =			 "language-based task representations, robot control",
  URL =			 "https://openreview.net/pdf?id=X128TIOXXw",
  crossref =		 "p11687"
}

@article{211001894,
  author =		 "Lutter, M. and  Peters, J.",
  year =		 "2023",
  title =		 "Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  URL =			 "https://arxiv.org/pdf/2110.01894.pdf",
  number =		 "3",
  crossref =		 "p11458"
}

@article{211001954,
  author =		 "Lutter, M. and  Belousov, B. and  Mannor, S. and  Fox, D. and  Garg, A. and  Peters, J.",
  year =		 "2023",
  title =		 "Continuous-Time Fitted Value Iteration for Robust Policies",
  booktitle =		 "IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://arxiv.org/pdf/2110.01954.pdf",
  crossref =		 "p11459"
}

@article{Loeckel_TSMC_2023,
  author =		 "Loeckel, S. and  Ju, S. and  Schaller, M. and  van Vliet, P.. and  Peters, J.",
  year =		 "2023",
  title =		 "An Adaptive Human Driver Model for Realistic Race Car Simulations",
  booktitle =		 "IEEE Transactions on Systems, Man and Cybernetics: Systems (TSMC)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/Loeckel_TSMC_2023.pdf",
  number =		 "11",
  pages =		 "6718-6730",
  crossref =		 "p11551"
}

@article{200608973,
  author =		 "Look, A. and  Kandemir, M. and  Rakitsch, B. and  Peters, J.",
  year =		 "2023",
  title =		 "A Deterministic Approximation to Neural SDEs",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://arxiv.org/pdf/2006.08973.pdf",
  number =		 "4",
  pages =		 "4023-4037",
  crossref =		 "p11547"
}

@inproceedings{Liu_ICTCPE_2023,
  author =		 "Liu, Y. and  Belousov, B. and  Funk, N. and  Chalvatzaki, G. and  Peters, J. and  Tessman, O.",
  year =		 "2023",
  title =		 "Auto(mated)nomous Assembly",
  booktitle =		 "International Conference on Trends on Construction in the Post-Digital Era",
  URL =			 "https://link.springer.com/chapter/10.1007/978-3-031-20241-4_12",
  publisher =		 "springer, cham",
  pages =		 "167-181",
  crossref =		 "p11567"
}

@inproceedings{ICRA_2023_ATACOM,
  author =		 "Liu, P. and  Zhang, K. and  Tateo, D. and  Jauhri, S. and  Hu, Z. and  Peters, J. Chalvatzaki, G.",
  year =		 "2023",
  title =		 "Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction",
  booktitle =		 "2023 IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PuzeLiu/ICRA_2023_ATACOM.pdf",
  publisher =		 "ieee",
  crossref =		 "p11564"
}

@inproceedings{2022__visual_tactile_sensor_based_force_estimation_for_position_force_teleoperation,
  author =		 "Zhu, Y. and  Nazirjonov, S. and  Jiang, B. and  Colan, J. and  Aoyama, T. and  Hasegawa, Y. and  Belousov, B. and  Hansel, K. and  Peters, J.",
  year =		 "2023",
  title =		 "Visual Tactile Sensor Based Force Estimation for Position-Force Teleoperation",
  booktitle =		 "IEEE International Conference on Cyborg and Bionic Systems (CBS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/KayHansel/2022__visual_tactile_sensor_based_force_estimation_for_position_force_teleoperation.pdf",
  pages =		 "49-52",
  crossref =		 "p11574"
}

@inproceedings{acceptedversion_Zelch_ICRA23,
  author =		 "Zelch, C. and  Peters, J. and  von Stryk, C.",
  year =		 "2023",
  title =		 "Start State Selection for Control Policy Learning from Optimal Trajectories",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Research/Overview/acceptedversion_Zelch_ICRA23.pdf",
  crossref =		 "p11575"
}

@inproceedings{2023se3graspurain,
  author =		 "Urain, J. and  Funk, N. and  Peters, J. and  Chalvatzaki G",
  year =		 "2023",
  title =		 "SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion",
  booktitle =		 "International Conference on Robotics and Automation (ICRA)",
  key =			 "se(3), 6d grasping, robotics, diffusion models",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JulenUrainDeJesus/2023se3graspurain.pdf",
  crossref =		 "p11579"
}

@inproceedings{hierarchical_policy_blending_as_inference_icra_2023,
  author =		 "Hansel, K. and  Urain, J. and  Peters, J. and  Chalvatzaki, G.",
  year =		 "2023",
  title =		 "Hierarchical Policy Blending as Inference for Reactive Robot Control",
  booktitle =		 "2023 IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/KayHansel/hierarchical_policy_blending_as_inference_icra_2023.pdf",
  publisher =		 "ieee",
  crossref =		 "p11581"
}

@inproceedings{le23a,
  author =		 "Le, A. T. and  Hansel, K. and  Peters, J. and  Chalvatzaki, G.",
  year =		 "2023",
  title =		 "Hierarchical Policy Blending As Optimal Transport",
  booktitle =		 "5th Annual Learning for Dynamics & Control Conference (L4DC)",
  URL =			 "https://proceedings.mlr.press/v211/le23a/le23a.pdf",
  publisher =		 "pmlr",
  crossref =		 "p11582"
}

@inproceedings{230212526,
  author =		 "Luis, C. and  Bottero, A.G. and  Vinogradska, J. and  Berkenkamp, F. and  Peters, J.",
  year =		 "2023",
  title =		 "Model-Based Uncertainty in Value Functions",
  booktitle =		 "Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)",
  URL =			 "https://arxiv.org/pdf/2302.12526.pdf",
  crossref =		 "p11583"
}

@inproceedings{pdfido3Q4m8jg4BR,
  author =		 "Al-Hafez, F. and  Tateo, D. and  Arenz, O. and  Zhao, G. and  Peters, J.",
  year =		 "2023",
  title =		 "LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  key =			 "inverse reinforcement learning, inverse q-learning, implicit reward regularization, imitation learning, locomotion",
  URL =			 "https://openreview.net/pdf?id=o3Q4m8jg4BR",
  crossref =		 "p11584"
}

@inproceedings{pdfidH4Ncs5jhTCu,
  author =		 "Palenicek, D. and  Lutter, M. and  Carvalho, J. and  Peters, J.",
  year =		 "2023",
  title =		 "Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "https://openreview.net/pdf?id=H4Ncs5jhTCu",
  crossref =		 "p11586"
}

@inproceedings{200605935,
  author =		 "Buechler, D. and  Guist, S. and  Calandra, R. and  Berenz, V. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2023",
  title =		 "Learning to Play Table Tennis From Scratch using Muscular Robots",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), IEEE T-TRo Track",
  URL =			 "https://arxiv.org/pdf/2006.05935.pdf",
  crossref =		 "p11589"
}

@inproceedings{urain_2023_liesvf,
  author =		 "Urain, J. and  Tateo, D. and  Peters, J.",
  year =		 "2023",
  title =		 "Learning Stable Vector Fields on Lie Groups",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), IEEE R-AL Track",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/urain_2023_liesvf.pdf",
  crossref =		 "p11591"
}

@article{2301,
  author =		 "Bjelonic, F. and  Lee, J. and  Arm, P. and  Sako, D. and  Tateo, D. and  Peters, J. and  Hutter, M.",
  year =		 "2023",
  title =		 "Learning-Based Design and Control for Quadrupedal Robots With Parallel-Elastic Actuators",
  booktitle =		 "IEEE Robotics and Automation Letters (R-AL)",
  URL =			 "https://arxiv.org/pdf/2301.03509",
  number =		 "3",
  pages =		 "1611-1618",
  crossref =		 "p11592"
}

@inproceedings{230304725,
  author =		 "Bethge, J. and  Pfefferkorn, M. and  Rose, A. and  Peters, J. and  Findeisen, R.",
  year =		 "2023",
  title =		 "Model predictive control with Gaussian-process-supported dynamical constraints for autonomous vehicles",
  booktitle =		 "Proceedings of the 22nd World Congress of the International Federation of Automatic Control",
  URL =			 "https://arxiv.org/pdf/2303.04725.pdf",
  crossref =		 "p11595"
}

@article{urain_2023_cep_ijrr,
  author =		 "Urain, J. and  Li, A. and  Liu, P. and  D'Eramo, C. and  Peters, J.",
  year =		 "2023",
  title =		 "Composable energy policies for reactive motion generation and reinforcement learning",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/urain_2023_cep_ijrr.pdf",
  crossref =		 "p11596"
}

@article{RAL_Siwei_Ju,
  author =		 "Ju, S. and  van Vliet, P. and  Arenz, O. and  Peters, J.",
  year =		 "2023",
  title =		 "Digital Twin of a Driver-in-the-Loop Race Car Simulation with Contextual Reinforcement Learning",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/RAL_Siwei_Ju.pdf",
  number =		 "7",
  pages =		 "4107-4114",
  crossref =		 "p11601"
}

@article{Peters_A_2023,
  author =		 "Peters, S. and  Peters, J. and  Findeisen, R.",
  year =		 "2023",
  title =		 "Quantifying Uncertainties along the Automated Driving Stack",
  booktitle =		 "ATZ worldwide volume",
  URL =			 "https://link.springer.com/article/10.1007/s38311-023-1489-8",
  pages =		 "62-65",
  crossref =		 "p11605"
}

@article{gmmvi,
  author =		 "Arenz, O. and  Dahlinger, P. and  Ye, Z. and  Volpp, M. and  Neumann, G.",
  year =		 "2023",
  title =		 "A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models",
  booktitle =		 "Transactions on Machine Learning Research (TMLR)",
  URL =			 "/uploads/Team/PubOlegArenz/gmmvi.pdf",
  crossref =		 "p11617"
}

@inproceedings{2308,
  author =		 "Carvalho, J. and  Le, A. T. and  Baierl, M. and  Koert, D. and  Peters, J.",
  year =		 "2023",
  title =		 "Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "motion planning, diffusion models",
  URL =			 "https://arxiv.org/abs/2308.01557",
  crossref =		 "p11609"
}

@inproceedings{pdfiddUO0QQw4FW,
  author =		 "Funk, N. and  Mueller, P.-O. and  Belousov, B. and  Savchenko, A. and  Findeisen, R. and  Peters, J.",
  year =		 "2023",
  title =		 "High-Resolution Pixelwise Contact Area and Normal Force Estimation for the GelSight Mini Visuotactile Sensor Using Neural Networks",
  booktitle =		 "Embracing Contacts-Workshop at ICRA 2023",
  URL =			 "https://openreview.net/pdf?id=dUO0QQw4FW",
  crossref =		 "p11611"
}

@article{pdf,
  author =		 "Scherf, L. and  Schmidt, A. and  Pal, S. and  Koert, D.",
  year =		 "2023",
  title =		 "Interactively learning behavior trees from imperfect human demonstrations",
  booktitle =		 "Frontiers in Robotics and AI",
  URL =			 "https://www.frontiersin.org/articles/10.3389/frobt.2023.1152595/pdf",
  crossref =		 "p11615"
}

@inproceedings{pdfid6dJGuVyR7K,
  author =		 "Vincent, T. and  Belousov, B. and  D'Eramo, C. and  Peters, J.",
  year =		 "2023",
  title =		 "Iterated Deep Q-Network: Efficient Learning of Bellman Iterations for Deep Reinforcement Learning",
  booktitle =		 "European Workshop on Reinforcement Learning (EWRL)",
  URL =			 "https://openreview.net/pdf?id=6dJGuVyR7K",
  crossref =		 "p11625"
}

@inproceedings{pdfidBcHDYvNgW4,
  author =		 "Al-Hafez, F. and  Tateo, D. and  Arenz, O. and  Zhao, G. and  Peters, J.",
  year =		 "2023",
  title =		 "Least Squares Inverse Q-Learning",
  booktitle =		 "European Workshop on Reinforcement Learning (EWRL)",
  URL =			 "https://openreview.net/pdf?id=BcHDYvNg-W4",
  crossref =		 "p11637"
}

@article{2305,
  author =		 "Look, A. and  Kandemir, M. and  Rakitsch, B. and  Peters, J.",
  year =		 "2023",
  title =		 "Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems",
  booktitle =		 "Transactions on Machine Learning Research (TMLR)",
  URL =			 "https://arxiv.org/abs/2305.01773",
  crossref =		 "p11650"
}

@inproceedings{mmucb2,
  author =		 "Flynn, H. and  Reeb, D. and  Kandemir, M. and  Peters, J.",
  year =		 "2023",
  title =		 "Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  URL =			 "/uploads/Team/HamishFlynn/mmucb2.pdf",
  crossref =		 "p11656"
}

@inproceedings{pli_final,
  author =		 "Gruner, T. and  Belousov, B. and  Muratore, F. and  Palenicek, D. and  Peters, J.",
  year =		 "2023",
  title =		 "Pseudo-Likelihood Inference",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  URL =			 "/uploads/Team/TheoGruner/pli_final",
  crossref =		 "p11659"
}

@inproceedings{mpot_preprint,
  author =		 "Le, A. T. and  Chalvatzaki, G. and  Biess, A. and  Peters, J.",
  year =		 "2023",
  title =		 "Accelerating Motion Planning via Optimal Transport",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/AnThaiLe/mpot_preprint.pdf",
  crossref =		 "p11660"
}

@inproceedings{pdfidGx62uPXEul,
  author =		 "Le, A. T. and  Chalvatzaki, G. and  Biess, A. and  Peters, J.",
  year =		 "2023",
  title =		 "Accelerating Motion Planning via Optimal Transport",
  booktitle =		 "IROS 2023 Workshop on Differentiable Probabilistic Robotics: Emerging Perspectives on Robot Learning",
  key =			 "motion planning, trajectory optimization, optimal transport",
  URL =			 "https://openreview.net/pdf?id=Gx62uPXEul",
  crossref =		 "p11670"
}

@inproceedings{ecai_2023,
  author =		 "Rother, D. and  Weisswange, T.H. and  Peters, J.",
  year =		 "2023",
  title =		 "Disentangling Interaction using Maximum Entropy Reinforcement Learning in Multi-Agent Systems",
  booktitle =		 "European Conference on Artificial Intelligence (ECAI)",
  key =			 "ad-hoc teamwork, maximum entropy reinforcement learning, coexistence, mixed motive",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/DavidRother/ecai_2023.pdf",
  crossref =		 "p11674"
}

@inproceedings{doctoral_consortium,
  author =		 "Rother, D.",
  year =		 "2023",
  title =		 "Implicitly Cooperative Agents through Impact-Aware Learning",
  booktitle =		 "European Conference on Artificial Intelligence (ECAI)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/DavidRother/doctoral_consortium.pdf",
  crossref =		 "p11675"
}

@inproceedings{pdfidUnNdjopNeW,
  author =		 "Vincent, T. and  Metelli, A. and  Peters, J. and  Restelli, M. and  D'Eramo, C.",
  year =		 "2023",
  title =		 "Parameterized projected Bellman operator",
  booktitle =		 "ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems",
  URL =			 "https://openreview.net/pdf?id=UnNdjopNeW",
  crossref =		 "p11676"
}

@inproceedings{human_preferences_and_robot_constraints_aware_shared_control,
  author =		 "Chen, Q. and  Zhu, Y. and  Hansel, Kay. and  Aoyama, T. and  Hasegawa, Y.",
  year =		 "2023",
  title =		 "Human Preferences and Robot Constraints Aware Shared Control for Smooth Follower Motion Execution",
  booktitle =		 "IEEE International Symposium on Micro-NanoMechatronics and Human Science (MHS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/KayHansel/human_preferences_and_robot_constraints_aware_shared_control.pdf",
  publisher =		 "ieee",
  crossref =		 "p11678"
}

@article{full,
  author =		 "Gu, S. and  Kshirsagar, A. and  Du Y. and  Chen G. and  Peters J. and  Knoll A.",
  year =		 "2023",
  title =		 "A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors",
  booktitle =		 "Frontiers in Neurorobotics",
  URL =			 "https://www.frontiersin.org/articles/10.3389/fnbot.2023.1280341/full",
  number =		 "1280341",
  crossref =		 "p11683"
}

@inproceedings{Mittenbuehler_CWLEAP_2023,
  author =		 "Mittenbuehler, M. and  Hendawy, A. and  D'Eramo, C. and  Chalvatzaki, G.",
  year =		 "2023",
  title =		 "Parameter-efficient Tuning of Pretrained Visual-Language Models in Multitask Robot Learning",
  booktitle =		 "CoRL 2023 Workshop on Learning Effective Abstractions for Planning (LEAP)",
  key =			 "pretrained visual-language models, multitask robot learning, adapters",
  crossref =		 "p11685"
}

@inproceedings{Metternich_NWGRL_2023,
  author =		 "Metternich, H. and  Hendawy, A. and  Klink, P. and  Peters, J. and  D'Eramo, C.",
  year =		 "2023",
  title =		 "Using Proto-Value Functions for Curriculum Generation in Goal-Conditioned RL",
  booktitle =		 "NeurIPS 2023 Workshop on Goal-Conditioned Reinforcement Learning",
  key =			 "reinforcement learning, curriculum learning, graph laplacian",
  crossref =		 "p11686"
}

@inproceedings{mpot_preprint,
  author =		 "Le, A. T. and  Chalvatzaki, G. and  Biess, A. and  Peters, J.",
  year =		 "2023",
  title =		 "Accelerating Motion Planning via Optimal Transport",
  booktitle =		 "NeurIPS 2023 Workshop Optimal Transport and Machine Learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/AnThaiLe/mpot_preprint.pdf",
  crossref =		 "p11691"
}

@inproceedings{boehm24_tart,
  author =		 "Boehm, A. and  Schneider, T. and  Belousov, B. and  Kshirsagar, A. and  Lin, L. and  Doerschner, K. and  Drewing, K. and  Rothkopf, C.A. and  Peters, J.",
  year =		 "2023",
  title =		 "Tactile Active Texture Recognition With Vision-Based Tactile Sensors",
  booktitle =		 "NeurIPS Workshop on Touch Processing: a new Sensing Modality for AI",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/boehm24_tart.pdf",
  crossref =		 "p11694"
}

@inproceedings{watson23rlws,
  author =		 "Watson, J. and  Peters, J. and ",
  year =		 "2023",
  title =		 "Sample-Efficient Online Imitation Learning using Pretrained Behavioural Cloning Policies",
  booktitle =		 "NeurIPS 6th Robot Learning Workshop: Pretraining, Fine-Tuning, and Generalization with Large Scale Models",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoeWatson/watson23rlws.pdf",
  crossref =		 "p11695"
}

@inproceedings{231102496,
  author =		 "Al-Hafez, F. and   Zhao, G. and  Peters, J. and  Tateo, D.",
  year =		 "2023",
  title =		 "LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion",
  booktitle =		 "Robot Learning Workshop, Conference on Neural Information Processing Systems (NeurIPS)",
  URL =			 "https://arxiv.org/pdf/2311.02496.pdf",
  crossref =		 "p11697"
}

@article{2001,
  author =		 "Parisi, S. and  Tateo, D. and  Hensel, M. and  D'Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "2022",
  title =		 "Long-Term Visitation Value for Deep Exploration in Sparse-Reward Reinforcement Learning",
  booktitle =		 "Algorithms",
  URL =			 "https://arxiv.org/abs/2001.00119",
  number =		 "3",
  pages =		 "81",
  crossref =		 "p11299"
}

@article{200605911,
  author =		 "Akrour, R. and  Tateo, D. and  Peters, J.",
  year =		 "2022",
  title =		 "Continuous Action Reinforcement Learning from a Mixture of Interpretable Experts",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://arxiv.org/pdf/2006.05911.pdf",
  number =		 "10",
  pages =		 "6795-6806",
  crossref =		 "p11386"
}

@article{004231142021,
  author =		 "Loeckel, S. and  Kretschi, A. and  van Vliet, P. and  Peters, J.",
  year =		 "2022",
  title =		 "Identification and modelling of race driving styles",
  booktitle =		 "Vehicle System Dynamics",
  URL =			 "https://doi.org/10.1080/00423114.2021.1930070",
  number =		 "8",
  pages =		 "2890--2918",
  crossref =		 "p11435"
}

@article{Tosatto_ITPAMI_2022,
  author =		 "Tosatto, S. and  Carvalho, J. and  Peters, J.",
  year =		 "2022",
  title =		 "Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://ieeexplore.ieee.org/document/9449972",
  number =		 "10",
  pages =		 "5996--6010",
  crossref =		 "p11436"
}

@article{pdfftmd5d34f2f24487d3e8e4c84d3d8a60a9f28pid1s20S092658052100457Xmain,
  author =		 "Belousov, B. and  Wibranek, B. and  Schneider, J. and  Schneider, T. and  Chalvatzaki, G. and  Peters, J. and  Tessmann, O.",
  year =		 "2022",
  title =		 "Robotic Architectural Assembly with Tactile Skills: Simulation and Optimization",
  booktitle =		 "Automation in Construction",
  URL =			 "https://www.sciencedirect.com/science/article/pii/S092658052100457X/pdfft?md5=d34f2f24487d3e8e4c84d3d8a60a9f28&pid=1-s2.0-S092658052100457X-main.pdf",
  pages =		 "104006",
  crossref =		 "p11461"
}

@article{RRC_v1,
  author =		 "Funk, N. and  Schaff, C. and  Madan, R. and  Yoneda, T. and  Urain, J. and  Watson, J. and  Gordon, E. and  Widmaier, F and  Bauer, S. and  Srinivasa, S. and  Bhattacharjee, T. and  Walter, M. and  Peters, J.",
  year =		 "2022",
  title =		 "Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation",
  booktitle =		 "IEEE Robotics and Automation Letters (R-AL)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/NiklasFunk/RRC_v1.pdf",
  crossref =		 "p11463"
}

@article{Muratore_RTYGPRobotLearningFromRandomizedSimulationsAReview,
  author =		 "Muratore, F. and  Ramos, F. and  Turk, G. and  Yu, W. and  Gienger, M. and  Peters, J.",
  year =		 "2022",
  title =		 "Robot Learning from Randomized Simulations: A Review",
  booktitle =		 "Frontiers in Robotics and AI",
  key =			 "robotics, simulation, reality gap, simulation optimization bias, reinforcement learning, domain randomization, sim-to-real",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/FabioMuratore/Muratore_RTYGP--RobotLearningFromRandomizedSimulations-AReview.pdf",
  crossref =		 "p11475"
}

@article{s10994021061036,
  author =		 "Cowen-Rivers, A.I. and  Palenicek, D. and  Moens, V. and  Abdullah, M.A. and  Sootla, A. and  Wang, J. and  Bou-Ammar, H.",
  year =		 "2022",
  title =		 "SAMBA: safe model-based & active reinforcement learning",
  booktitle =		 "Machine Learning",
  URL =			 "https://link.springer.com/article/10.1007/s10994-021-06103-6",
  crossref =		 "p11482"
}

@article{Integrating_Contrastive_Learning_with_Dynamic_Models_for_Reinforcement_Learning_from_Images,
  author =		 "You, B. and  Arenz, O. and  Chen, Y. and  Peters, J.",
  year =		 "2022",
  title =		 "Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images",
  booktitle =		 "Neurocomputing",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/OlegArenz/Integrating_Contrastive_Learning_with_Dynamic_Models_for_Reinforcement_Learning_from_Images.pdf",
  crossref =		 "p11484"
}

@inproceedings{boostedcrl,
  author =		 "Klink, P. and  D`Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "2022",
  title =		 "Boosted Curriculum Reinforcement Learning",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PascalKlink/boosted-crl.pdf",
  crossref =		 "p11486"
}

@inproceedings{AISTATS2022_DRCREPS,
  author =		 "Memmel, M. and  Liu, P. and  Tateo, D. and  Peters, J.",
  year =		 "2022",
  title =		 "Dimensionality Reduction and Prioritized Exploration for Policy Search",
  booktitle =		 "25th International Conference on Artificial Intelligence and Statistics (AISTATS)",
  key =			 "policy search, dimensionality reduction, exploration",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PuzeLiu/AISTATS2022_DR-CREPS.pdf",
  crossref =		 "p11487"
}

@article{220303303,
  author =		 "Flynn, H. and  Reeb, D. and  Kandemir, M. and  Peters, J.",
  year =		 "2022",
  title =		 "PAC-Bayesian Lifelong Learning For Multi-Armed Bandits",
  booktitle =		 "Data Mining and Knowledge Discovery",
  URL =			 "https://arxiv.org/pdf/2203.03303.pdf",
  number =		 "2",
  pages =		 "841-876",
  crossref =		 "p11488"
}

@article{s1236902100763z,
  author =		 "Prasad, V. and  Stock-Homburg, R. and  Peters, J.",
  year =		 "2022",
  title =		 "Human-Robot Handshaking: A Review",
  booktitle =		 "International Journal of Social Robotics (IJSR)",
  key =			 "handshaking, physical hri, social robotics",
  URL =			 "https://link.springer.com/content/pdf/10.1007/s12369-021-00763-z.pdf",
  number =		 "1",
  pages =		 "277-293",
  crossref =		 "p11493"
}

@article{Zheng_ITR_2022,
  author =		 "Zheng, Y. and  Veiga, F.F. and  Peters, J. and  Santos, V.J.",
  year =		 "2022",
  title =		 "Autonomous Learning of Page Flipping Movements via Tactile Feedback",
  booktitle =		 "IEEE Transactions on Robotics (T-Ro)",
  URL =			 "https://ieeexplore.ieee.org/document/9786532",
  number =		 "5",
  pages =		 "2734 - 2749",
  crossref =		 "p11494"
}

@inproceedings{220314660,
  author =		 "Palenicek, D. and  Lutter, M., Peters, J.",
  year =		 "2022",
  title =		 "Revisiting Model-based Value Expansion",
  booktitle =		 "Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  URL =			 "https://arxiv.org/pdf/2203.14660.pdf",
  crossref =		 "p11498"
}

@article{robustRLsurvey22_hansel,
  author =		 "Hansel, K. and  Moos, J. and  Abdulsamad, H. and  Stark, S. and  Clever, D. and  Peters, J.",
  year =		 "2022",
  title =		 "Robust Reinforcement Learning: A Review of Foundations and Recent Advances",
  booktitle =		 "Machine Learning and Knowledge Extraction (MAKE)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/KayHansel/robustRLsurvey22_hansel.pdf",
  publisher =		 "mdpi",
  number =		 "1",
  pages =		 "276--315",
  ISBN/ISSN =		 "2504-4990",
  crossref =		 "p11499"
}

@unpublished{Carvalho_MCRLDM_2022,
  author =		 "Carvalho, J. and  Peters, J.",
  year =		 "2022",
  title =		 "An Analysis of Measure-Valued Derivatives for Policy Gradients",
  booktitle =		 "Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  URL =			 "https://arxiv.org/pdf/2203.03917.pdf",
  crossref =		 "p11501"
}

@article{FinalSubmission1,
  author =		 "Weng, Y. and  Pajarinen, J. and  Akrour, R. and  Matsuda, T. and  Peters, J. and  Maki, T.",
  year =		 "2022",
  title =		 "Reinforcement Learning Based Underwater Wireless Optical Communication Alignment for Multiple Autonomous Underwater Vehicles",
  booktitle =		 "IEEE Journal of Oceanic Engineering",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Research/Overview/FinalSubmission-1.pdf",
  number =		 "4",
  pages =		 "1231-1245",
  crossref =		 "p11506"
}

@article{200605935,
  author =		 "Buechler, D. and  Guist, S. and  Calandra, R. and  Berenz, V. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2022",
  title =		 "Learning to Play Table Tennis From Scratch using Muscular Robots",
  booktitle =		 "IEEE Transactions on Robotics (T-Ro)",
  URL =			 "https://arxiv.org/pdf/2006.05935.pdf",
  number =		 "6",
  pages =		 "3850-3860",
  crossref =		 "p11509"
}

@inproceedings{crrt,
  author =		 "Klink, P. and  Yang, H. and  D'Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "2022",
  title =		 "Curriculum Reinforcement Learning via Constrained Optimal Transport",
  booktitle =		 "International Conference on Machine Learning (ICML)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PascalKlink/crrt.pdf",
  crossref =		 "p11521"
}

@article{Weng_IPTL_2022,
  author =		 "Weng, Y. and  Matsuda, T. and  Sekimuri, Y. and  Pajarinen, J. and  Peters, J. and  Maki, T.",
  year =		 "2022",
  title =		 "Pointing Error Control of Underwater Wireless Optical Communication on Mobile Platform",
  booktitle =		 "IEEE Photonics Technology Letters",
  URL =			 "https://ieeexplore.ieee.org/document/9791364",
  number =		 "13",
  pages =		 "699-702",
  crossref =		 "p11529"
}

@article{201203826,
  author =		 "Cowen-Rivers, A. and  Lyu, W. and  Tutunov, R. and  Wang, Z. and  Grosnit, A. and  Griffiths, R.R. and  Maraval, A. and  Jianye, H. and  Wang, J. and  Peters, J. and  Bou Ammar, H.",
  year =		 "2022",
  title =		 "HEBO: An Empirical Study of Assumptions in Bayesian Optimisation",
  booktitle =		 "Journal of Artificial Intelligence Research",
  URL =			 "https://arxiv.org/pdf/2012.03826.pdf",
  pages =		 "1269-1349",
  crossref =		 "p11530"
}

@inproceedings{iros2022_ebmtrajopt,
  author =		 "Urain, J. and  Le, A. T. and  Lambert, A. and  Chalvatzaki, G. and  Boots, B. and  Peters, J.",
  year =		 "2022",
  title =		 "Learning Implicit Priors for Motion Optimization",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "motion planning, energy-based models",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/AnThaiLe/iros2022_ebmtrajopt.pdf",
  crossref =		 "p11531"
}

@inproceedings{IROS_2022_ReDSDF,
  author =		 "Liu, P. and  Zhang, K. and  Tateo, D. and  Jauhri, S. and  Peters, J. and  Chalvatzaki, G. and ",
  year =		 "2022",
  title =		 "Regularized Deep Signed Distance Fields for Reactive Motion Generation",
  booktitle =		 "2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PuzeLiu/IROS_2022_ReDSDF.pdf",
  crossref =		 "p11533"
}

@inproceedings{IROS22_3682_MS,
  author =		 "Zheng, Y. and  Veiga, F.F. and  Peters, J. and  Santos, V.J.",
  year =		 "2022",
  title =		 "Autonomous Learning of Page Flipping Movements via Tactile Feedback",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Member/FilipeVeiga/IROS22_3682_MS.pdf",
  crossref =		 "p11535"
}

@inproceedings{GNN_meets_MILP_v1,
  author =		 "Funk, N. and  Menzenbach, S. and  Chalvatzaki, G. and  Peters, J.",
  year =		 "2022",
  title =		 "Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/NiklasFunk/GNN_meets_MILP_v1.pdf",
  crossref =		 "p11537"
}

@inproceedings{2207,
  author =		 "Ploeger, K. and  Peters, J.",
  year =		 "2022",
  title =		 "Controlling the Cascade: Kinematic Planning for N-ball Toss Juggling",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://arxiv.org/abs/2207.01414",
  crossref =		 "p11538"
}

@inproceedings{221012806,
  author =		 "Schneider, T. and  Belousov, B. and  Chalvatzaki, G. and  Romeres, D. and  Jha, D.K. and  Peters, J.",
  year =		 "2022",
  title =		 "Active Exploration for Robotic Manipulation",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://arxiv.org/pdf/2210.12806.pdf",
  crossref =		 "p11548"
}

@inproceedings{220610313,
  author =		 "Schneider, T. and  Belousov, B. and  Abdulsamad, H. and  Peters, J.",
  year =		 "2022",
  title =		 "Active Inference for Robotic Manipulation",
  booktitle =		 "5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  key =			 "robotic manipulation, model-based reinforcement learning, information gain",
  URL =			 "https://arxiv.org/pdf/2206.10313.pdf",
  crossref =		 "p11549"
}

@inproceedings{Galljamov_IICHR_2022,
  author =		 "Galljamov, R. and  Zhao, G. and  Belousov, B. and  Seyfarth, A. and  Peters, J.",
  year =		 "2022",
  title =		 "Improving Sample Efficiency of Example-Guided Deep Reinforcement Learning for Bipedal Walking",
  booktitle =		 "2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)",
  URL =			 "https://ieeexplore.ieee.org/document/10000068",
  crossref =		 "p11550"
}

@inproceedings{watson22corl,
  author =		 "Watson, J. and  Peters, J.",
  year =		 "2022",
  title =		 "Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes",
  booktitle =		 "Conference on Robot Learning (CoRL)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoeWatson/watson22corl.pdf",
  crossref =		 "p11552"
}

@inproceedings{Adapting_Object_Centric_Probabilistic_Movement_Primitives_with_Residual_Reinforcement_Learning___compressed,
  author =		 "Carvalho, J. and  Koert, D. and  Daniv, M. and  Peters, J.",
  year =		 "2022",
  title =		 "Adapting Object-Centric Probabilistic Movement Primitives with Residual Reinforcement Learning",
  booktitle =		 "2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoaoCarvalho/Adapting_Object_Centric_Probabilistic_Movement_Primitives_with_Residual_Reinforcement_Learning___compressed.pdf",
  crossref =		 "p11556"
}

@inproceedings{IntegratedBiManualMotionGenerationandControlshapedforProMPs,
  author =		 "Vorndamme, J. and  Carvalho, J. and  Laha, R. and  Koert, D. and  Figueredo, L. and  Peters, J. and  Haddadin, S.",
  year =		 "2022",
  title =		 "Integrated Bi-Manual Motion Generation and Control shaped for Probabilistic Movement Primitives",
  booktitle =		 "2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoaoCarvalho/IntegratedBiManualMotionGenerationandControlshapedforProMPs.pdf",
  crossref =		 "p11557"
}

@inproceedings{Scherf_Humanoids_2022_final,
  author =		 "Scherf, L. and  Turan, C. and  Koert, D.",
  year =		 "2022",
  title =		 "Learning from Unreliable Human Action Advice in Interactive Reinforcement Learning",
  booktitle =		 "2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/LisaScherf/Scherf_Humanoids_2022_final.pdf",
  crossref =		 "p11558"
}

@inproceedings{HUMANOIDS22MILDHRI,
  author =		 "Prasad, V. and  Koert, D. and  Stock-Homburg, R. and  Peters, J. and  Chalvatzaki, G.",
  year =		 "2022",
  title =		 "MILD: Multimodal Interactive Latent Dynamics for Learning Human-Robot Interaction",
  booktitle =		 "IEEE-RAS International Conference on Humanoid Robots (Humanoids)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/VigneshPrasad/HUMANOIDS22-MILD-HRI.pdf",
  crossref =		 "p11560"
}

@unpublished{Conditioned_Score_Based_Models_for_Learning_Collision_Free_Trajectory_Generation,
  author =		 "Carvalho, J. and  Baierl, M and  Urain, J and  Peters, J.",
  year =		 "2022",
  title =		 "Conditioned Score-Based Models for Learning Collision-Free Trajectory Generation",
  booktitle =		 "NeurIPS 2022 Workshop on Score-Based Methods",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoaoCarvalho/Conditioned_Score_Based_Models_for_Learning_Collision_Free_Trajectory_Generation.pdf",
  crossref =		 "p11561"
}

@inproceedings{221114655,
  author =		 "Siebenborn, M. and  Belousov, B. and  Huang, J. and  Peters, J.",
  year =		 "2022",
  title =		 "How Crucial is Transformer in Decision Transformer?",
  booktitle =		 "Foundation Models for Decision Making Workshop at Neural Information Processing Systems",
  URL =			 "https://arxiv.org/pdf/2211.14655.pdf",
  crossref =		 "p11568"
}

@article{2022msvfurain,
  author =		 "Urain, J. and  Tateo, D and  Peters, J.",
  year =		 "2022",
  title =		 "Learning Stable Vector Fields on Lie Groups",
  booktitle =		 "Robotics and Automation Letters (RA-L)",
  key =			 "imitation learning, lie groups, learning from demonstration, machine learning for robot control, reactive motion generation.",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JulenUrainDeJesus/2022msvfurain.pdf",
  crossref =		 "p11580"
}

@inproceedings{Watson_RWDSR_2022,
  author =		 "Watson, J. and  Hanher, B. and  Peters, J.",
  year =		 "2022",
  title =		 "Differentiable Simulators as Gaussian Processes",
  booktitle =		 "R:SS Workshop: Differentiable Simulation for Robotics",
  crossref =		 "p11622"
}

@inproceedings{Watson_TMCRLDM_2022,
  author =		 "Watson, J. and  Peters, J. and ",
  year =		 "2022",
  title =		 "Stationary Posterior Policy Iteration with Variational Inference",
  booktitle =		 "The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  crossref =		 "p11623"
}

@inproceedings{c628644624c1be9c8cfb1541fa6421fdPaperConference,
  author =		 "Bottero, A.G. and  Luis, C.E. and  Vinogradska, J. and  Berkenkamp, F. and  Peters, J.",
  year =		 "2022",
  title =		 "Information-Theoretic Safe Exploration with Gaussian Processes",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  URL =			 "https://proceedings.neurips.cc/paper_files/paper/2022/file/c628644624c1be9c8cfb1541fa6421fd-Paper-Conference.pdf",
  crossref =		 "p11671"
}

@inproceedings{Le_RWIRRM_2022,
  author =		 "Le, A. T. and  Urain, J. and  Lambert, A. and  Chalvatzaki, G. and  Boots, B. and  Peters, J.",
  year =		 "2022",
  title =		 "Learning Implicit Priors for Motion Optimization",
  booktitle =		 "RSS 2022 Workshop on Implicit Representations for Robotic Manipulation",
  crossref =		 "p11692"
}

@article{Muratore_Gienger_PetersAssessingTransferabilityfromSimulationToRealityForReinforcementLearning,
  author =		 "Muratore, F. and  Gienger, M. and  Peters, J.",
  year =		 "2021",
  title =		 "Assessing Transferability from Simulation to Reality for Reinforcement Learning",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/FabioMuratore/Muratore_Gienger_Peters--AssessingTransferabilityfromSimulationToRealityForReinforcementLearning.pdf",
  publisher =		 "ieee",
  number =		 "4",
  pages =		 "1172-1183",
  ISBN/ISSN =		 "0162-8828",
  crossref =		 "p11288"
}

@article{Rawal_FRA_2021,
  author =		 "Rawal, N. and  Koert, D. and  Turan, C. and  Kersting, K. and  Peters, J. and  Stock-Homburg, R.",
  year =		 "2021",
  title =		 "ExGenNet: Learning to Generate Robotic Facial Expression Using Facial Expression Recognition",
  booktitle =		 "Frontiers in Robotics & AI",
  URL =			 "https://www.frontiersin.org/articles/10.3389/frobt.2021.730317/full",
  number =		 "730317",
  crossref =		 "p11492"
}

@article{tosattomdpi2021,
  author =		 "Tosatto, S. and  Akrour, R. and  Peters, J.",
  year =		 "2021",
  title =		 "An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions",
  booktitle =		 "Stats",
  key =			 "nonparametric, bias, kernel regression",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Alumni/SamueleTosatto/tosatto-mdpi-2021.pdf",
  pages =		 "1--17",
  crossref =		 "p11331"
}

@article{200302471,
  author =		 "Muratore, F. and  Eilers, C. and  Gienger, M. and  Peters, J.",
  year =		 "2021",
  title =		 "Data-efficient Domain Randomization with Bayesian Optimization",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L), with Presentation at the IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "sim-2-real, domain randomization, bayesian optimization",
  URL =			 "https://arxiv.org/pdf/2003.02471.pdf",
  publisher =		 "ieee",
  crossref =		 "p11340"
}

@article{201203806,
  author =		 "Hoefer, S. and  Bekris, K. and  Handa, A. and  Gamboa, J.C. and  Golemo, F. and  Mozifian, M. and  Atkeson, C.G., Fox, D. and  Goldberg, K. and  Leonard, J. and  Liu, C.K. and  Peters, J. and  Song, S. and  Welinder, P. and  White, M.",
  year =		 "2021",
  title =		 "Sim2Real in Robotics and Automation: Applications and Challenges",
  booktitle =		 "IEEE Transactions on Automation Science (T-ASE)",
  URL =			 "https://arxiv.org/pdf/2012.03806.pdf",
  number =		 "2",
  pages =		 "398-400",
  crossref =		 "p11417"
}

@article{201107016,
  author =		 "Akrour, R. and  Atamna, A. and  Peters, J.",
  year =		 "2021",
  title =		 "Convex Optimization with an Interpolation-based Projection and its Application to Deep Learning",
  booktitle =		 "Machine Learning (MACH)",
  URL =			 "https://arxiv.org/pdf/2011.07016.pdf",
  number =		 "8",
  pages =		 "2267-2289",
  crossref =		 "p11385"
}

@book{Belousov_SCI_2021,
  author =		 "Belousov, B. and  Abdulsamad H. and  Klink, P. and  Parisi, S. and  Peters, J.",
  year =		 "2021",
  title =		 "Reinforcement Learning Algorithms: Analysis and Applications",
  booktitle =		 "Studies in Computational Intelligence",
  URL =			 "https://www.springer.com/gp/book/9783030411879",
  publisher =		 "springer international publishing",
  edition =		 "1",
  crossref =		 "p11390"
}

@inproceedings{AABI21,
  author =		 "Watson, J. and  Lin, J. A. and  Klink, P. and  Peters, J.",
  year =		 "2021",
  title =		 "Neural Linear Models with Functional Gaussian Process Priors",
  booktitle =		 "3rd Symposium on Advances in Approximate Bayesian Inference (AABI)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoeWatson/AABI21.pdf",
  crossref =		 "p11392"
}

@inproceedings{cdc21,
  author =		 "Watson, J. and  Peters, J.",
  year =		 "2021",
  title =		 "Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk",
  booktitle =		 "American Control Conference (ACC)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoeWatson/cdc21.pdf",
  crossref =		 "p11393"
}

@inproceedings{AISTATS21,
  author =		 "Watson, J. and  Lin J. A. and  Klink, P. and  Pajarinen, J. and  Peters, J.",
  year =		 "2021",
  title =		 "Latent Derivative Bayesian Last Layer Networks",
  booktitle =		 "Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoeWatson/AISTATS21.pdf",
  crossref =		 "p11394"
}

@article{2102,
  author =		 "Klink, P. and  Abdulsamad, H. and  Belousov, B. and  D'Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "2021",
  title =		 "A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  URL =			 "http://arxiv.org/abs/2102.13176",
  crossref =		 "p11408"
}

@inproceedings{201013766,
  author =		 "Tosatto, S. and  Chalvatzaki, G. and  Peters, J.",
  year =		 "2021",
  title =		 "Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://arxiv.org/pdf/2010.13766.pdf",
  crossref =		 "p11409"
}

@inproceedings{Li_PIICRA_2021,
  author =		 "Li, Q. and  Chalvatzaki, G. and  Peters, J. and  Wang, Y.",
  year =		 "2021",
  title =		 "Directed Acyclic Graph Neural Network for Human Motion Prediction",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://ieeexplore.ieee.org/document/9561540",
  crossref =		 "p11412"
}

@inproceedings{ICRA22Prasad,
  author =		 "Prasad, V. and  Stock-Homburg, R. and  Peters, J.",
  year =		 "2021",
  title =		 "Learning Human-like Hand Reaching for Human-Robot Handshaking",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/VigneshPrasad/ICRA22-Prasad.pdf",
  crossref =		 "p11413"
}

@inproceedings{LutterICRA2021,
  author =		 "Lutter, M. and  Silberbauer, J. and  Watson, J. and  Peters, J.",
  year =		 "2021",
  title =		 "Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoeWatson/LutterICRA2021.pdf",
  crossref =		 "p11414"
}

@inproceedings{Morgan_PIICRA_2021,
  author =		 "Morgan, A. and  Nandha, D. and  Chalvatzaki, G. and  D'Eramo, C. and  Dollar, A. and  Peters, J.",
  year =		 "2021",
  title =		 "Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://ieeexplore.ieee.org/document/9561298",
  crossref =		 "p11415"
}

@inproceedings{Abdulsamad_PIICRA_2021,
  author =		 "Abdulsamad, H. and  Nickl, P. and  Klink, P. and  Peters, J.",
  year =		 "2021",
  title =		 "A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://arxiv.org/pdf/2011.05217.pdf",
  crossref =		 "p11416"
}

@inproceedings{200700391,
  author =		 "Dam, T. and  D'Eramo, C. and  Peters, J. and  Pajarinen J.",
  year =		 "2021",
  title =		 "Convex Regularization in Monte-Carlo Tree Search",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  URL =			 "https://arxiv.org/pdf/2007.00391.pdf",
  crossref =		 "p11418"
}

@article{210314610,
  author =		 "Tanneberg, D. and  Ploeger, K. and  Rueckert, E. and  Peters, J.",
  year =		 "2021",
  title =		 "SKID RAW: Skill Discovery from Raw Trajectories",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L)",
  key =			 "goal-robots, skills4robots",
  URL =			 "https://arxiv.org/pdf/2103.14610.pdf",
  crossref =		 "p11419"
}

@inproceedings{210315388,
  author =		 "Abdulsamad, H. and  Dorau, T. and  Belousov, B. and  Zhu, J.-J and  Peters, J.",
  year =		 "2021",
  title =		 "Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative Entropy Trust-Regions",
  booktitle =		 "arXiv",
  URL =			 "https://arxiv.org/pdf/2103.15388.pdf",
  crossref =		 "p11421"
}

@inproceedings{2021_ijcnnmvd_rl,
  author =		 "Carvalho, J., Tateo, D., Muratore, F., Peters, J.",
  year =		 "2021",
  title =		 "An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients",
  booktitle =		 "International Joint Conference on Neural Networks (IJCNN)",
  key =			 "measure-valued derivative, policy gradient, reinforcement learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoaoCarvalho/2021_ijcnn-mvd_rl.pdf",
  crossref =		 "p11427"
}

@inproceedings{210504682,
  author =		 "Lutter, M. and  Mannor, S. and  Peters, J. and  Fox, D. and  Garg, A.",
  year =		 "2021",
  title =		 "Value Iteration in Continuous Actions, States and Time",
  booktitle =		 "International Conference on Machine Learning (ICML)",
  URL =			 "https://arxiv.org/pdf/2105.04682.pdf",
  crossref =		 "p11429"
}

@inproceedings{210512189,
  author =		 "Lutter, M. and  Mannor, S. and  Peters, J. and  Fox, D. and  Garg, A.",
  year =		 "2021",
  title =		 "Robust Value Iteration for Continuous Control Tasks",
  booktitle =		 "Robotics: Science and Systems (RSS)",
  URL =			 "https://arxiv.org/pdf/2105.12189.pdf",
  crossref =		 "p11430"
}

@article{Learn_etc_v1,
  author =		 "Funk, N. and  Baumann, D. and  Berenz, V. and  Trimpe, S.",
  year =		 "2021",
  title =		 "Learning event-triggered control from data through joint optimization",
  booktitle =		 "IFAC Journal of Systems and Control",
  key =			 "event-triggered control, reinforcement learning, stability verification, neural networks",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/NiklasFunk/Learn_etc_v1.pdf",
  pages =		 "100144",
  ISBN/ISSN =		 "2468-6018",
  crossref =		 "p11431"
}

@inproceedings{cep_rss_2021,
  author =		 "Urain, J. and  Li, A. and  Liu, P. and  D'Eramo, C. and  Peters, J.",
  year =		 "2021",
  title =		 "Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning",
  booktitle =		 "Robotics: Science and Systems (RSS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JulenUrainDeJesus/cep_rss_2021.pdf",
  crossref =		 "p11432"
}

@inbook{Hansel_RLAAA_2021,
  author =		 "Hansel, K. and  Moos, J. and  Derstroff, C.",
  year =		 "2021",
  title =		 "Benchmarking the Natural Gradient in Policy Gradient Methods and Evolution Strategies",
  booktitle =		 "Reinforcement Learning Algorithms: Analysis and Applications",
  URL =			 "https://link.springer.com/chapter/10.1007/978-3-030-41188-6_7",
  publisher =		 "springer",
  pages =		 "69--84",
  crossref =		 "p11433"
}

@inproceedings{Lutter_PIICASE_2021,
  author =		 "Lutter, M. and  Clever, D. and  Kirsten, R. and  Listmann, K. and  Peters, J.",
  year =		 "2021",
  title =		 "Building Skill Learning Systems for Robotics",
  booktitle =		 "Proceedings of the IEEE International Conference on Automation Science and Engineering (CASE)",
  URL =			 "https://ieeexplore.ieee.org/document/9551562",
  crossref =		 "p11440"
}

@inproceedings{Knaust_PICHR_2021,
  author =		 "Knaust, M. and  Koert, D.",
  year =		 "2021",
  title =		 "Guided Robot Skill Learning: A User-Study on Learning Probabilistic Movement Primitives with Non-Experts",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "kobo",
  URL =			 "https://ieeexplore.ieee.org/document/9555785",
  crossref =		 "p11441"
}

@article{Lampariello_JGCD_2021,
  author =		 "Lampariello, R. and  Mishra, H. and  Oumer, N.W. and  Peters, J.",
  year =		 "2021",
  title =		 "Robust Motion Prediction of a Free-Tumbling Satellite with On-Ground Experimental Validation",
  booktitle =		 "Journal of Guidance, Control, and Dynamics",
  URL =			 "https://arc.aiaa.org/doi/pdf/10.2514/1.G005745",
  number =		 "10",
  pages =		 "1777-1793",
  crossref =		 "p11442"
}

@inproceedings{IROS_2021_Air_Hockey,
  author =		 "Liu, P. and  Tateo, D. and  Bou-Ammar, H. and  Peters, J.",
  year =		 "2021",
  title =		 "Efficient and Reactive Planning for High Speed Robot Air Hockey",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PuzeLiu/IROS_2021_Air_Hockey.pdf",
  crossref =		 "p11446"
}

@inproceedings{Muratore_GWBPGNeuralPosteriorDomainRandomization,
  author =		 "Muratore, F. and  Gruner, T. and  Wiese, F. and  Belousov, B. and  Gienger, M. and  Peters, J.",
  year =		 "2021",
  title =		 "Neural Posterior Domain Randomization",
  booktitle =		 "Conference on Robot Learning (CoRL)",
  key =			 "sim-to-real, domain randomization, likelihood-free inference",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/FabioMuratore/Muratore_GWBPG--NeuralPosteriorDomainRandomization.pdf",
  crossref =		 "p11452"
}

@inproceedings{ecaade2021_247,
  author =		 "Wibranek, B. and  Liu, Y. and  Funk, N. and  Belousov, B. and  Peters, J. and  Tessmann, O.",
  year =		 "2021",
  title =		 "Reinforcement Learning for Sequential Assembly of SL-Blocks: Self-Interlocking Combinatorial Design Based on Machine Learning",
  booktitle =		 "Proceedings of the 39th eCAADe Conference",
  key =			 "skills4robots",
  URL =			 "http://papers.cumincad.org/data/works/att/ecaade2021_247.pdf",
  crossref =		 "p11454"
}

@article{ArmSym_elib,
  author =		 "Bustamante, S. and  Peters, J. and   Schoelkopf, B. and   Grosse-Wentrup, M. and  Jayaram, V.",
  year =		 "2021",
  title =		 "ArmSym: a virtual human-robot interaction laboratory for assistive robotics",
  booktitle =		 "IEEE Transactions on Human-Machine Systems",
  URL =			 "https://elib.dlr.de/147359/1/ArmSym_elib.pdf",
  number =		 "6",
  pages =		 "568-577",
  crossref =		 "p11455"
}

@article{18056,
  author =		 "D`Eramo, C. and  Tateo, D and  Bonarini, A. and  Restelli, M. and  Peters, J.",
  year =		 "2021",
  title =		 "MushroomRL: Simplifying Reinforcement Learning Research",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  URL =			 "https://jmlr.org/papers/volume22/18-056/18-056.pdf",
  number =		 "131",
  pages =		 "1-5",
  crossref =		 "p11462"
}

@article{20633,
  author =		 "D`Eramo, C. and  Cini, A. and  Nuara, A. and  Pirotta, M. and  Alippi, C. and  Peters, J. and  Restelli, M.",
  year =		 "2021",
  title =		 "Gaussian Approximation for Bias Reduction in Q-Learning",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  URL =			 "https://www.jmlr.org/papers/volume22/20-633/20-633.pdf",
  crossref =		 "p11465"
}

@inproceedings{L2A_v1,
  author =		 "Funk, N. and  Chalvatzaki, G. and  Belousov, B. and  Peters, J.",
  year =		 "2021",
  title =		 "Learn2Assemble with Structured Representations and Search for Robotic Architectural Construction",
  booktitle =		 "Conference on Robot Learning (CoRL)",
  key =			 "structured representations, autonomous assembly, manipulation",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/NiklasFunk/L2A_v1.pdf",
  crossref =		 "p11466"
}

@inproceedings{CORL_2021_Learning_on_the_Manifold,
  author =		 "Liu, P. and  Tateo, D. and  Bou-Ammar, H. and  Peters, J.",
  year =		 "2021",
  title =		 "Robot Reinforcement Learning on the Constraint Manifold",
  booktitle =		 "Proceedings of the Conference on Robot Learning (CoRL)",
  key =			 "robot learning, constrained reinforcement learning, safe exploration",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PuzeLiu/CORL_2021_Learning_on_the_Manifold.pdf",
  crossref =		 "p11469"
}

@article{211106211,
  author =		 "Abdulsamad, H. and  Peters, J.",
  year =		 "2021",
  title =		 "Model-Based Reinforcement Learning for Stochastic Hybrid Systems",
  booktitle =		 "arXiv",
  URL =			 "https://arxiv.org/pdf/2111.06211.pdf",
  crossref =		 "p11477"
}

@inbook{Palenicek_RLAAA_2021,
  author =		 "Palenicek, D.",
  year =		 "2021",
  title =		 "A Survey on Constraining Policy Updates Using the KL Divergence",
  booktitle =		 "Reinforcement Learning Algorithms: Analysis and Applications",
  URL =			 "https://link.springer.com/chapter/10.1007/978-3-030-41188-6_5",
  pages =		 "49-57",
  crossref =		 "p11483"
}

@inproceedings{bauer22a,
  author =		 "Bauer, S. and  Wüthrich, W. and  Widmaier, F. and  Buchholz, A. and  Stark, S. and  Goyal, A. and  Steinbrenner, T. and  Akpo, J. and  Joshi, S. and  Berenz, V. and  Agrawal, V. and  Funk, N. and  Urain, J. and  Peters, J. and  Watson, J. and  Et, A.L.l",
  year =		 "2021",
  title =		 "Real Robot Challenge: A Robotics Competition in the Cloud",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  URL =			 "https://proceedings.mlr.press/v176/bauer22a/bauer22a.pdf",
  crossref =		 "p11672"
}

@article{pdf,
  author =		 "Veiga, F. F. and  Edin B.B and  Peters, J.",
  year =		 "2020",
  title =		 "Grip Stabilization through Independent Finger Tactile Feedback Control",
  booktitle =		 "Sensors (Special Issue on Sensors and Robot Control)",
  URL =			 "https://www.mdpi.com/1424-8220/20/6/1748/pdf",
  crossref =		 "p11151"
}

@article{NuQuPS_preprint,
  author =		 "Vinogradska, J. and  Bischoff, B. and  Koller, T. and  Achterhold, J. and  Peters, J.",
  year =		 "2020",
  title =		 "Numerical Quadrature for Probabilistic Policy Search",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NuQuPS_preprint.pdf",
  number =		 "1",
  pages =		 "164-175",
  crossref =		 "p11167"
}

@article{Lioutikov_IJRR_2020,
  author =		 "Lioutikov, R. and  Maeda, G. and  Veiga, F.F. and  Kersting, K. and  Peters, J.",
  year =		 "2020",
  title =		 "Learning Attribute Grammars for Movement Primitive Sequencing",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  key =			 "skillz4robots",
  number =		 "1",
  pages =		 "21-38",
  crossref =		 "p11218"
}

@article{VIPS_JMLR,
  author =		 "Arenz, O. and  Zhong, M. and  Neumann G.",
  year =		 "2020",
  title =		 "Trust-Region Variational Inference with Gaussian Mixture Models",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  key =			 "approximate inference, variational inference, sampling, policy search, mcmc, markov chain monte carlo",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/OlegArenz/VIPS_JMLR.pdf",
  crossref =		 "p11247"
}

@article{180810648,
  author =		 "Gomez-Gonzalez, S. and  Neumann, G. and  Schölkopf, B. and  Peters, J.",
  year =		 "2020",
  title =		 "Adaptation and Robust Learning of Probabilistic Movement Primitives",
  booktitle =		 "IEEE Transactions on Robotics (T-Ro)",
  URL =			 "https://arxiv.org/pdf/1808.10648.pdf",
  number =		 "2",
  pages =		 "366-379",
  crossref =		 "p11260"
}

@article{Koert_IJHR_2020,
  author =		 "Koert, D. and  Trick, S. and  Ewerton, M. and  Lutter, M. and  Peters, J.",
  year =		 "2020",
  title =		 "Incremental Learning of an Open-Ended Collaborative Skill Library",
  booktitle =		 "International Journal of Humanoid Robotics (IJHR)",
  key =			 "skills4robots, kobo",
  URL =			 "https://www.worldscientific.com/doi/10.1142/S0219843620500012",
  number =		 "1",
  crossref =		 "p11291"
}

@inproceedings{0332,
  author =		 "Dam, T. and  Klink, P. and  D'Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "2020",
  title =		 "Generalized Mean Estimation in Monte-Carlo Tree Search",
  booktitle =		 "Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)",
  URL =			 "https://www.ijcai.org/Proceedings/2020/0332.pdf",
  crossref =		 "p11293"
}

@article{200108255,
  author =		 "Loeckel, S. and  Peters, J. and  van Vliet, P.",
  year =		 "2020",
  title =		 "A Probabilistic Framework for Imitating Human Race Driver Behavior",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L), with Presentation at the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://arxiv.org/pdf/2001.08255.pdf",
  number =		 "2",
  crossref =		 "p11319"
}

@inproceedings{Motokura_IRALPIICRA_2020,
  author =		 "Motokura, K. and  Takahashi, M. and  Ewerton, M. and  Peters, J.",
  year =		 "2020",
  title =		 "Plucking Motions for Tea Harvesting Robots Using Probabilistic Movement Primitives",
  booktitle =		 "IEEE Robotics and Automation Letters (ICRA/RA-L), with Presentation at the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://ieeexplore.ieee.org/document/9013082",
  number =		 "2",
  pages =		 "2377-3766",
  crossref =		 "p11321"
}

@inproceedings{Zelch_ICRA_2020,
  author =		 "Zelch, C. and  Peters, J. and  von Stryk, O.",
  year =		 "2020",
  title =		 "Learning Control Policies from Optimal Trajectories",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/Members/Zelch_ICRA_2020.pdf",
  crossref =		 "p11322"
}

@article{190903895,
  author =		 "Gomez-Gonzalez, S. and  Prokudin, S. and  Schölkopf, B. and  Peters, J.",
  year =		 "2020",
  title =		 "Real Time Trajectory Prediction Using Deep Conditional Generative Models",
  booktitle =		 "IEEE Robotics and Automation Letters (ICRA/RA-L), with Presentation at the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://arxiv.org/pdf/1909.03895.pdf",
  number =		 "2",
  pages =		 "970-976",
  crossref =		 "p11308"
}

@inproceedings{tosatto2020,
  author =		 "Tosatto, S. and  Carvalho, J. and  Abdulsamad, H. and  Peters, J.",
  year =		 "2020",
  title =		 "A Nonparametric Off-Policy Policy Gradient",
  booktitle =		 "Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS)",
  key =			 "nonparametric, policy gradient, off policy, reinforcement learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SamueleTosatto/tosatto2020.pdf",
  crossref =		 "p11316"
}

@inproceedings{pdfidrkgpv2VFvr,
  author =		 "D`Eramo, C. and   Tateo, D. and  Bonarini, A. and  Restelli, M. and  Peters, J.",
  year =		 "2020",
  title =		 "Sharing Knowledge in Multi-Task Deep Reinforcement Learning",
  booktitle =		 "International Conference in Learning Representations (ICLR)",
  URL =			 "https://openreview.net/pdf?id=rkgpv2VFvr",
  crossref =		 "p11317"
}

@inproceedings{Eilers_Eschmann_Menzenbach_BMPUnderactuatedWaypointTrajectoryOptimizationforLightPaintingPhotography,
  author =		 "Eilers, C. and  Eschmann, J. and  Menzenbach, R. and  Belousov, B. and  Muratore, F. and  Peters, J.",
  year =		 "2020",
  title =		 "Underactuated Waypoint Trajectory Optimization for Light Painting Photography",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/FabioMuratore/Eilers_Eschmann_Menzenbach_BMP--UnderactuatedWaypointTrajectoryOptimizationforLightPaintingPhotography.pdf",
  crossref =		 "p11325"
}

@inproceedings{HRI20RSH,
  author =		 "Stock-Homburg, R. and  Peters, J. and  Schneider, K. and  Prasad, V. and  Nukovic, L.",
  year =		 "2020",
  title =		 "Evaluation of the Handshake Turing Test for anthropomorphic Robots",
  booktitle =		 "Proceedings of the ACM/IEEE International Conference on Human Robot Interaction (HRI), Late Breaking Report",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/VigneshPrasad/HRI20-RSH.pdf",
  crossref =		 "p11332"
}

@techreport{tosatto2020b,
  author =		 "Tosatto, S. and  Stadtmueller, J. and  Peters, J.",
  year =		 "2020",
  title =		 "Dimensionality Reduction of Movement Primitives in Parameter Space",
  booktitle =		 "arXiv",
  key =			 "movement primitives, dimensionality reduction, imitation learning, robot learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SamueleTosatto/tosatto2020b.pdf",
  crossref =		 "p11341"
}

@inproceedings{20_ISGTEU_SanMorPetSte_paper,
  author =		 "Almeida Santos, A. and  Gil, C.E.M. and  Peters, J. and  Steinke, F.",
  year =		 "2020",
  title =		 "Decentralized Data-Driven Tuning of Droop Frequency Controllers",
  booktitle =		 "2020 IEEE PES Innovative Smart Grid Technologies Europe",
  URL =			 "https://www.eins.tu-darmstadt.de/fileadmin/user_upload/publications_pdf/20_ISGTEU_SanMorPetSte_paper.pdf",
  crossref =		 "p11344"
}

@inproceedings{2005,
  author =		 "Abdulsamad, H. and  Peters, J.",
  year =		 "2020",
  title =		 "Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation",
  booktitle =		 "2nd Annual Conference on Learning for Dynamics and Control",
  URL =			 "https://arxiv.org/abs/2005.01432",
  crossref =		 "p11347"
}

@article{200805251,
  author =		 "Ewerton, M. and   Arenz, O. and  Peters, J.",
  year =		 "2020",
  title =		 "Assisted Teleoperation in Changing Environments with a Mixture of Virtual Guides",
  booktitle =		 "Advanced Robotics",
  URL =			 "https://arxiv.org/pdf/2008.05251.pdf",
  crossref =		 "p11352"
}

@inproceedings{beckerEIM,
  author =		 "Becker, P. and  Arenz, O. and  Neumann, G.",
  year =		 "2020",
  title =		 "Expected Information Maximization: Using the I-Projection for Mixture Density Estimation",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "/uploads/Team/OlegArenz/beckerEIM.pdf",
  crossref =		 "p11363"
}

@article{200702084,
  author =		 "Lauri, M. and  Pajarinen, J. and  Peters, J. and  Frintrop, S.",
  year =		 "2020",
  title =		 "Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L)",
  URL =			 "https://arxiv.org/pdf/2007.02084.pdf",
  number =		 "4",
  pages =		 "5323-5330",
  crossref =		 "p11356"
}

@article{190204524,
  author =		 "Agudelo-Espana, D. and  Gomez-Gonzalez, S. and  Bauer, S. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2020",
  title =		 "Bayesian Online Prediction of Change Points",
  booktitle =		 "Conference on Uncertainty in Artificial Intelligence (UAI)",
  URL =			 "https://arxiv.org/pdf/1902.04524.pdf",
  crossref =		 "p11357"
}

@inproceedings{Melvin_Iros,
  author =		 "Laux, M. and  Arenz, O. and  Pajarinen, J. and  Peters, J.",
  year =		 "2020",
  title =		 "Deep  Adversarial  Reinforcement  Learning  for  Object  Disentangling",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020)",
  URL =			 "/uploads/Site/EditPublication/Melvin_Iros.pdf",
  crossref =		 "p11362"
}

@article{multi_channel_feedback_rl_sequential,
  author =		 "Koert, D. and  Kircher, M. and  Salikutluk, V. and  D'Eramo, C. and  Peters, J.",
  year =		 "2020",
  title =		 "Multi-Channel Interactive Reinforcement Learning for Sequential Tasks",
  booktitle =		 "Frontiers in Robotics and AI Human-Robot Interaction",
  key =			 "skills4robots, kobo",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/DorotheaKoert/multi_channel_feedback_rl_sequential.pdf",
  crossref =		 "p11366"
}

@techreport{nail_arxiv,
  author =		 "Arenz, O. and  Neumann, G.",
  year =		 "2020",
  title =		 "Non-Adversarial Imitation Learning and its Connections to Adversarial Methods",
  booktitle =		 "arXiv",
  key =			 "imitation learning, inverse reinforcement learning, non-adversarial imitation learning, adversarial imitation learning, airl",
  URL =			 "/uploads/Team/OlegArenz/nail_arxiv.pdf",
  crossref =		 "p11367"
}

@unpublished{HapticbasedGuidedGraspinginaClutteredEnvironment,
  author =		 "Abi-Farraj, F. and  Pacchierotti, C. and  Arenz, O. and  Neumann, G. and  Giordano, P.",
  year =		 "2020",
  title =		 "Haptic-based Guided Grasping in a Cluttered Environment",
  booktitle =		 "IEEE Haptics Symposium",
  URL =			 "https://www.roboticvision.org/wp-content/uploads/Haptic-based-Guided-Grasping-in-a-Cluttered-Environment.pdf",
  crossref =		 "p11368"
}

@inproceedings{200804589,
  author =		 "Keller, L. and  Tanneberg, D. and  Stark, S. and  Peters, J.",
  year =		 "2020",
  title =		 "Model-Based Quality-Diversity Search for Efficient Robot Learning",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "goal-robots, skills4robots",
  URL =			 "https://arxiv.org/pdf/2008.04589.pdf",
  crossref =		 "p11369"
}

@inproceedings{neurips20202,
  author =		 "Klink, P. and  D'Eramo, C. and  Peters, J. and  Pajarinen, J.",
  year =		 "2020",
  title =		 "Self-Paced Deep Reinforcement Learning",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PascalKlink/neurips-2020-2.pdf",
  crossref =		 "p11374"
}

@inproceedings{201013483,
  author =		 "Ploeger, K. and  Lutter, M. and  Peters, J.",
  year =		 "2020",
  title =		 "High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards",
  booktitle =		 "Conference on Robot Learning (CoRL)",
  URL =			 "https://arxiv.org/pdf/2010.13483.pdf",
  crossref =		 "p11375"
}

@inproceedings{2020iflowurain,
  author =		 "Urain, J. and  Ginesi, M. and  Tateo, D. and  Peters, J.",
  year =		 "2020",
  title =		 "ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems",
  key =			 "movement primitives, imitation learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JulenUrainDeJesus/2020iflowurain.pdf",
  crossref =		 "p11377"
}

@inproceedings{Abdulsamad_EWDCML_2020,
  author =		 "Abdulsamad, H. and  Peters, J.",
  year =		 "2020",
  title =		 "Learning Hybrid Dynamics and Control",
  booktitle =		 "ECML/PKDD Workshop on Deep Continuous-Discrete Machine Learning",
  crossref =		 "p11379"
}

@article{210507957,
  author =		 "Tanneberg, D. and  Rueckert, E. and  Peters, J.",
  year =		 "2020",
  title =		 "Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers",
  booktitle =		 "Nature Machine Intelligence",
  key =			 "goal-robots, skills4robots",
  URL =			 "https://arxiv.org/pdf/2105.07957.pdf",
  number =		 "12",
  pages =		 "753-763",
  crossref =		 "p11380"
}

@article{Veiga_FRA_2020,
  author =		 "Veiga, F. F. and  Akrour, R. and  Peters, J.",
  year =		 "2020",
  title =		 "Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks",
  booktitle =		 "Frontiers in Robotics and AI",
  URL =			 "https://www.frontiersin.org/articles/10.3389/frobt.2020.521448/full",
  crossref =		 "p11384"
}

@inproceedings{2020_structuredpolicy_urain,
  author =		 "Urain, J. and  Tateo, D. and  Ren, T. and  Peters, J.",
  year =		 "2020",
  title =		 "Structured policy representation: Imposing stability in arbitrarily conditioned dynamic systems",
  booktitle =		 "NeurIPS 2020, 3rd Robot Learning Workshop",
  key =			 "movement primitives, imitation learning, inductive bias",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JulenUrainDeJesus/2020_structuredpolicy_urain.pdf",
  pages =		 "7",
  crossref =		 "p11388"
}

@inproceedings{Watson_IWAI_2020,
  author =		 "Watson, J. and  Imohiosen A. and  Peters, J.",
  year =		 "2020",
  title =		 "Active Inference or Control as Inference? A Unifying View",
  booktitle =		 "International Workshop on Active Inference",
  crossref =		 "p11395"
}

@inproceedings{ICSR21Prasad,
  author =		 "Prasad, V. and  Stock-Homburg, R. and  Peters, J.",
  year =		 "2020",
  title =		 "Advances in Human-Robot Handshaking",
  booktitle =		 "International Conference on Social Robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/VigneshPrasad/ICSR21-Prasad.pdf",
  publisher =		 "springer",
  crossref =		 "p11399"
}

@inproceedings{Lutter_ISR_2020,
  author =		 "Lutter, M. and  Clever, D. and  Belousov, B. and  Listmann, K. and  Peters, J.",
  year =		 "2020",
  title =		 "Evaluating the Robustness of HJB Optimal Feedback Control",
  booktitle =		 "International Symposium on Robotics",
  crossref =		 "p11460"
}

@inproceedings{content,
  author =		 "Rother, D., Haider, T., & Eger, S",
  year =		 "2020",
  title =		 "CMCE at SemEval-2020 Task 1: Clustering on Manifolds of Contextualized Embeddings to Detect Historical Meaning Shifts",
  booktitle =		 "14th International Workshop on Semantic Evaluation (SemEval)",
  key =			 "natural language processing, unsupervised clustering, semantic shift detection, semantic evaluation",
  URL =			 "https://pure.mpg.de/rest/items/item_3278784/component/file_3278792/content",
  pages =		 "187-193",
  crossref =		 "p11673"
}

@inproceedings{Lutter_RSARLW_2020,
  author =		 "Lutter, M. and  Silberbauer, J. and  Watson, J. and  Peters, J.",
  year =		 "2020",
  title =		 "A Differentiable Newton Euler Algorithm for Multi-body Model Learning",
  booktitle =		 "R:SS Structured Approaches to Robot Learning Workshop",
  crossref =		 "p11693"
}

@article{tanneberg_NN18,
  author =		 "Tanneberg, D. and  Peters, J. and  Rueckert, E.",
  year =		 "2019",
  title =		 "Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks",
  booktitle =		 "Neural Networks",
  key =			 "goal-robots, skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/DanielTanneberg/tanneberg_NN18.pdf",
  pages =		 "67-80",
  crossref =		 "p11134"
}

@article{Learning_to_Serve_2019,
  author =		 "Koc, O. and  Peters, J.",
  year =		 "2019",
  title =		 "Learning to serve: an experimental study for a new learning from demonstrations framework",
  booktitle =		 "IEEE Robotics and Automation Letters (ICRA/RA-L), with Presentation at the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Learning_to_Serve_2019.pdf",
  crossref =		 "p11168"
}

@inproceedings{1902,
  author =		 "Lauri, M. and  Pajarinen, J. and  Peters, J.",
  year =		 "2019",
  title =		 "Information gathering in decentralized POMDPs by policy graph improvement",
  booktitle =		 "Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS)",
  key =			 "roboleap,skills4robots",
  URL =			 "https://arxiv.org/pdf/1902.09840",
  crossref =		 "p11190"
}

@article{florian_ral_sub,
  author =		 "Brandherm, F. and  Peters, J. and  Neumann, G. and  Akrour, R.",
  year =		 "2019",
  title =		 "Learning Replanning Policies with Direct Policy Search",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/RiadAkrour/florian_ral_sub.pdf",
  crossref =		 "p11191"
}

@article{TheKernelKalmanRuleJournal,
  author =		 "Gebhardt, G.H.W. and  Kupcsik, A. and  Neumann, G.",
  year =		 "2019",
  title =		 "The Kernel Kalman Rule",
  booktitle =		 "Machine Learning Journal (MLJ)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/GregorGebhardt/TheKernelKalmanRuleJournal.pdf",
  publisher =		 "springer us",
  number =		 "12",
  pages =		 "2113–2157",
  ISBN/ISSN =		 "0885-6125",
  crossref =		 "p11172"
}

@article{parisi2019mlj,
  author =		 "Parisi, S. and  Tangkaratt, V. and  Peters, J. and  Khan, M. E.",
  year =		 "2019",
  title =		 "TD-Regularized Actor-Critic Methods",
  booktitle =		 "Machine Learning (MLJ)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SimoneParisi/parisi2019mlj.pdf",
  number =		 "8",
  pages =		 "1467-1501",
  crossref =		 "p11184"
}

@inproceedings{lutter_iclr_2019,
  author =		 "Lutter, M. and  Ritter, C. and  Peters, J.",
  year =		 "2019",
  title =		 "Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning",
  booktitle =		 "International Conference on Learning Representations (ICLR)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/MichaelLutter/lutter_iclr_2019.pdf",
  crossref =		 "p11185"
}

@article{180701918,
  author =		 "Koc, O. and  Maeda, G. and  Peters, J.",
  year =		 "2019",
  title =		 "Optimizing the Execution of Dynamic Robot Movements with Learning Control",
  booktitle =		 "IEEE Transactions on Robotics",
  URL =			 "https://arxiv.org/pdf/1807.01918.pdf",
  number =		 "4",
  pages =		 "1552-3098",
  crossref =		 "p11193"
}

@inproceedings{TosattoIJCNN2019,
  author =		 "Tosatto, S. and  D'Eramo, C. and  Pajarinen, J. and  Restelli, M. and  Peters, J.",
  year =		 "2019",
  title =		 "Exploration Driven By an Optimistic Bellman Equation",
  booktitle =		 "Proceedings of the International Joint Conference on Neural Networks (IJCNN)",
  key =			 "exploration and  reinforcement learning and  intrinsic motivation and  bosch-forschungstiftung",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SamueleTosatto/TosattoIJCNN2019.pdf",
  crossref =		 "p11194"
}

@inproceedings{wibranek_caad19,
  author =		 "Wibranek, B. and  Belousov, B. and  Sadybakasov, A. and  Tessmann, O.",
  year =		 "2019",
  title =		 "Interactive Assemblies: Man-Machine Collaboration through Building Components for As-Built Digital Models",
  booktitle =		 "Computer-Aided Architectural Design Futures (CAAD Futures)",
  key =			 "skills4robots",
  URL =			 "/uploads/Team/BorisBelousov/wibranek_caad19.pdf",
  crossref =		 "p11201"
}

@article{abi_farrajTOHsharedcontrolgrasping,
  author =		 "Abi Farraj, F. and  Pacchierotti, C. and  Arenz, O. and  Neumann, G. and  Giordano, P.",
  year =		 "2019",
  title =		 "A Haptic Shared-Control Architecture for Guided Multi-Target Robotic Grasping",
  booktitle =		 "IEEE Transactions on Haptics",
  key =			 "grasping, task analysis, manipulators, grippers, service robots",
  URL =			 "https://inria.hal.science/hal-02113206/file/abi_farraj-TOH-sharedcontrol-grasping.pdf",
  crossref =		 "p11209"
}

@inproceedings{papi,
  author =		 "Akrour, R. and  Pajarinen, J. and  Neumann, G. and  Peters, J.",
  year =		 "2019",
  title =		 "Projections for Approximate Policy Iteration Algorithms",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  key =			 "roboleap,skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/RiadAkrour/papi.pdf",
  crossref =		 "p11206"
}

@inproceedings{190512434,
  author =		 "Becker-Ehmck, P. and  Peters, J. and  van der Smagt, P.",
  year =		 "2019",
  title =		 "Switching Linear Dynamics for Variational Bayes Filtering",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  URL =			 "https://arxiv.org/pdf/1905.12434.pdf",
  crossref =		 "p11207"
}

@inproceedings{rldm19_belousov,
  author =		 "Belousov, B. and  Abdulsamad, H. and  Schultheis, M. and  Peters, J.",
  year =		 "2019",
  title =		 "Belief Space Model Predictive Control for Approximately Optimal System Identification",
  booktitle =		 "4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  key =			 "skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/rldm19_belousov.pdf",
  crossref =		 "p11211"
}

@article{entropy19_belousov,
  author =		 "Belousov, B. and  Peters, J.",
  year =		 "2019",
  title =		 "Entropic Regularization of Markov Decision Processes",
  booktitle =		 "Entropy",
  key =			 "skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/entropy19_belousov.pdf",
  publisher =		 "mdpi",
  number =		 "7",
  ISBN/ISSN =		 "1099-4300",
  crossref =		 "p11244"
}

@article{1010072Fs10994019058070,
  author =		 "Pajarinen, J. and  Thai, H.L. and  Akrour, R. and  Peters, J. and  Neumann, G.",
  year =		 "2019",
  title =		 "Compatible natural gradient policy search",
  booktitle =		 "Machine Learning (MLJ)",
  key =			 "roboleap,skills4robots",
  URL =			 "https://link.springer.com/content/pdf/10.1007%2Fs10994-019-05807-0.pdf",
  publisher =		 "springer",
  number =		 "8",
  pages =		 "1443--1466",
  crossref =		 "p11228"
}

@article{IJRR__Revision_,
  author =		 "Celemin, C. and  Maeda, G. and  Peters, J. and  Ruiz-del-Solar, J. and  Kober, J.",
  year =		 "2019",
  title =		 "Reinforcement Learning of Motor Skills using Policy Search and Human Corrective Advice",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Alumni/JensKober/IJRR__Revision_.pdf",
  number =		 "14",
  crossref =		 "p11237"
}

@inproceedings{iros19_nass_v2,
  author =		 "Nass, D. and  Belousov, B. and  Peters, J.",
  year =		 "2019",
  title =		 "Entropic Risk Measure in Policy Search",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/iros19_nass_v2.pdf",
  crossref =		 "p11238"
}

@inproceedings{190709533,
  author =		 "Ozdenizci, O. and  Meyer, T. and  Wichmann, F. and  Peters, J. and  Schoelkopf B. and  Cetin, M. and  Grosse-Wentrup, M.",
  year =		 "2019",
  title =		 "Neural Signatures of Motor Skill in the Resting Brain",
  booktitle =		 "Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC)",
  URL =			 "https://arxiv.org/pdf/1907.09533.pdf",
  crossref =		 "p11239"
}

@inproceedings{julen_IROS_2019,
  author =		 "Urain, J. and  Peters, J.",
  year =		 "2019",
  title =		 "Generalized  Multiple  Correlation  Coefficient  as  a  Similarity Measurement  between  Trajectories",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "2019",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JulenUrainDeJesus/julen_IROS_2019.pdf",
  crossref =		 "p11240"
}

@inproceedings{IROS_2019_Final_DeLaN_Energy_Control,
  author =		 "Lutter, M. and  Peters, J.",
  year =		 "2019",
  title =		 "Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems",
  booktitle =		 "International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/MichaelLutter/IROS_2019_Final_DeLaN_Energy_Control.pdf",
  crossref =		 "p11241"
}

@article{final_ral_2019_koert,
  author =		 "Koert, D. and  Pajarinen, J. and  Schotschneider, A. and  Trick, S., Rothkopf, C. and   Peters, J.",
  year =		 "2019",
  title =		 "Learning Intention Aware Online Adaptation of Movement Primitives",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L), with presentation at the IEEE International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "skills4robots, kobo",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/DorotheaKoert/final_ral_2019_koert.pdf",
  crossref =		 "p11243"
}

@inproceedings{celik2019chance,
  author =		 "Celik, O. and  Abdulsamad, H. and  Peters, J.",
  year =		 "2019",
  title =		 "Chance-Constrained Trajectory Optimization for Nonlinear Systems with Unknown Stochastic Dynamics",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/HanyAbdulsamad/celik2019chance.pdf",
  crossref =		 "p11245"
}

@inproceedings{RLDM2019_Deep_Optimal_Control,
  author =		 "Lutter, M. and  Peters, J.",
  year =		 "2019",
  title =		 "Deep Optimal Control: Using the Euler-Lagrange Equation to learn an Optimal Feedback Control Law",
  booktitle =		 "Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/MichaelLutter/RLDM2019_Deep_Optimal_Control.pdf",
  crossref =		 "p11267"
}

@inproceedings{190702426,
  author =		 "Trick, S. and  Koert, D. and  Peters, J. and  Rothkopf, C.",
  year =		 "2019",
  title =		 "Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "skills4robots, kobo",
  URL =			 "https://arxiv.org/pdf/1907.02426.pdf",
  crossref =		 "p11250"
}

@inproceedings{stark_iros2019_update,
  author =		 "Stark, S. and  Peters, J. and  Rueckert, E.",
  year =		 "2019",
  title =		 "Experience Reuse with Probabilistic Movement Primitives",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "goal-robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SvenjaStark/stark_iros2019_update.pdf",
  crossref =		 "p11251"
}

@inproceedings{Liu_IROS_2019,
  author =		 "Liu, Z. and  Hitzmann, A. and  Ikemoto, S. and  Stark, S. and  Peters, J. and  Hosoda, K.",
  year =		 "2019",
  title =		 "Local Online Motor Babbling: Learning Motor Abundance of a Musculoskeletal Robot Arm",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SvenjaStark/Liu_IROS_2019.pdf",
  crossref =		 "p11252"
}

@inproceedings{belousov19_fingervision,
  author =		 "Belousov, B. and  Sadybakasov, A. and  Wibranek, B. and  Veiga, F. and  Tessmann, O. and  Peters, J.",
  year =		 "2019",
  title =		 "Building a Library of Tactile Skills Based on FingerVision",
  booktitle =		 "Proceedings of the 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)",
  key =			 "skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/belousov19_fingervision.pdf",
  crossref =		 "p11261"
}

@inproceedings{schultheis19_rhc,
  author =		 "Schultheis, M. and  Belousov, B. and  Abdulsamad, H. and  Peters, J.",
  year =		 "2019",
  title =		 "Receding Horizon Curiosity",
  booktitle =		 "Proceedings of the 3rd Conference on Robot Learning (CoRL)",
  key =			 "skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/schultheis19_rhc.pdf",
  crossref =		 "p11265"
}

@inproceedings{CoRL2019_Deep_Optimal_HJB_Control,
  author =		 "Lutter, M. and  Belousov, B. and  Listmann, K. and  Clever, D. and  Peters, J.",
  year =		 "2019",
  title =		 "HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints",
  booktitle =		 "Conference on Robot Learning (CoRL)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/MichaelLutter/CoRL2019_Deep_Optimal_HJB_Control.pdf",
  crossref =		 "p11266"
}

@article{full,
  author =		 "Ewerton, M. and   Arenz, O. and  Maeda, G. and  Koert, D. and  Kolev, Z. and  Takahashi, M. and  Peters, J.",
  year =		 "2019",
  title =		 "Learning Trajectory Distributions for Assisted Teleoperation and Path Planning",
  booktitle =		 "Frontiers in Robotics and AI",
  URL =			 "https://www.frontiersin.org/articles/10.3389/frobt.2019.00089/full",
  crossref =		 "p11268"
}

@inproceedings{Ewerton_IROS_2019,
  author =		 "Ewerton, M. and  Maeda, G. and  Koert, D. and  Kolev, Z. and  Takahashi, M. and  Peters, J.",
  year =		 "2019",
  title =		 "Reinforcement Learning of Trajectory Distributions: Applications in Assisted Teleoperation and Motion Planning",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Member/PubMarcoEwerton/Ewerton_IROS_2019.pdf",
  pages =		 "4294--4300",
  crossref =		 "p11269"
}

@inproceedings{wibranek_sigradi19,
  author =		 "Wibranek, B. and  Belousov, B. and  Sadybakasov, A. and  Peters, J. and  Tessmann, O.",
  year =		 "2019",
  title =		 "Interactive Structure: Robotic Repositioning of Vertical Elements in Man-Machine Collaborative Assembly through Vision-Based Tactile Sensing",
  booktitle =		 "Proceedings of the 37th eCAADe and 23rd SIGraDi Conference",
  key =			 "skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/wibranek_sigradi19.pdf",
  crossref =		 "p11270"
}

@inproceedings{sprl,
  author =		 "Klink, P. and  Abdulsamad, H. and  Belousov, B. and  Peters, J.",
  year =		 "2019",
  title =		 "Self-Paced Contextual Reinforcement Learning",
  booktitle =		 "Proceedings of the 3rd Conference on Robot Learning (CoRL)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/PascalKlink/sprl.pdf",
  crossref =		 "p11272"
}

@inproceedings{Watson19I2c,
  author =		 "Watson, J. and  Abdulsamad, H. and  Peters, J.",
  year =		 "2019",
  title =		 "Stochastic Optimal Control as Approximate Input Inference",
  booktitle =		 "Conference on Robot Learning (CoRL)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JoeWatson/Watson19I2c.pdf",
  crossref =		 "p11273"
}

@inproceedings{Abdulsamad_MCRLDM_2019,
  author =		 "Abdulsamad, H. and  Naveh, K. and  Peters, J.",
  year =		 "2019",
  title =		 "Model-Based Relative Entropy Policy Search for Stochastic Hybrid Systems",
  booktitle =		 "4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  crossref =		 "p11274"
}

@article{GomezGonzalez,_R_2019,
  author =		 "Gomez Gonzalez, S. and  Nemmour, Y. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2019",
  title =		 "Reliable Real Time Ball Tracking for Robot Table Tennis",
  booktitle =		 "Robotics",
  URL =			 "https://www.mdpi.com/2218-6581/8/4/90",
  number =		 "4",
  crossref =		 "p11284"
}

@article{Schuermann_FN_2019,
  author =		 "Schuermann, T. and  Mohler, B.J. and  Peters, J. and  Beckerle, P.",
  year =		 "2019",
  title =		 "How Cognitive Models of Human Body Experience Might Push Robotics",
  booktitle =		 "Frontiers in Neurorobotics",
  crossref =		 "p11289"
}

@inproceedings{delfosse_iros2019,
  author =		 "Delfosse, Q. and  Stark, S. and  Tanneberg, D. and  Santucci, V. G. and  Peters, J.",
  year =		 "2019",
  title =		 "Open-Ended Learning of Grasp Strategies using Intrinsically Motivated Self-Supervision",
  booktitle =		 "Workshop at the  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "goal-robots, skills4robots",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SvenjaStark/delfosse_iros2019.pdf",
  crossref =		 "p11292"
}

@inproceedings{Muratore_GPRLDM_2019,
  author =		 "Muratore, F. and  Gienger, M. and  Peters, J.",
  year =		 "2019",
  title =		 "Assessing Transferability in Reinforcement Learning from Randomized Simulations",
  booktitle =		 "Reinforcement Learning and Decision Making (RLDM)",
  key =			 "domain randomization, simulation optimization, sim-2-real",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/FabioMuratore/Muratore_GP--RLDM_2019.pdf",
  crossref =		 "p11330"
}

@inproceedings{Look_NBW_2019,
  author =		 "Look, A. and  Kandemir, M.",
  year =		 "2019",
  title =		 "Differential Bayesian Neural Nets",
  booktitle =		 "NeurIPS Bayesian Workshop",
  crossref =		 "p11339"
}

@techreport{Tanneberg__2019,
  author =		 "Tanneberg, D. and  Rueckert, E. and  Peters, J.",
  year =		 "2019",
  title =		 "Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture",
  booktitle =		 "arXiv",
  key =			 "goal-robots, skills4robots",
  URL =			 "https://arxiv.org/pdf/1911.00926.pdf",
  crossref =		 "p11381"
}

@inproceedings{Klink_MCRLDM_2019,
  author =		 "Klink, P. and  Peters, J.",
  year =		 "2019",
  title =		 "Measuring Similarities between Markov Decision Processes",
  booktitle =		 "4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM)",
  crossref =		 "p11391"
}

@article{KroemerAuRo17Updated2,
  author =		 "Kroemer, O. and  Leischnig, S. and  Luettgen, S. and  Peters, J.",
  year =		 "2018",
  title =		 "A Kernel-based Approach to Learning Contact Distributions for Robot Manipulation Tasks",
  booktitle =		 "Autonomous Robots (AURO)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Alumni/OliverKroemer/KroemerAuRo17Updated2.pdf",
  number =		 "3",
  pages =		 "581-600",
  crossref =		 "p11076"
}

@article{promps_auro,
  author =		 "Paraschos, A. and  Daniel, C. and   Peters, J. and  Neumann, G.",
  year =		 "2018",
  title =		 "Using Probabilistic Movement Primitives in Robotics",
  booktitle =		 "Autonomous Robots (AURO)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/AlexandrosParaschos/promps_auro.pdf",
  number =		 "3",
  pages =		 "529-551",
  crossref =		 "p11077"
}

@article{SNA2018yi,
  author =		 "Yi, Z. and  Zhang, Y. and  Peters, J.",
  year =		 "2018",
  title =		 "Biomimetic Tactile Sensors and Signal Processing with Spike Trains: A Review",
  booktitle =		 "Sensors & Actuators: A. Physical",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/SNA2018yi.pdf",
  pages =		 "41-52",
  crossref =		 "p11094"
}

@article{Paraschos_AR_2018,
  author =		 "Paraschos, A. and  Rueckert, E. and  Peters, J. and  Neumann, G.",
  year =		 "2018",
  title =		 "Probabilistic Movement Primitives under Unknown System Dynamics",
  booktitle =		 "Advanced Robotics (ARJ)",
  URL =			 "https://www.ias.tu-darmstadt.de/uploads/Alumni/AlexandrosParaschos/Paraschos_AR_2018.pdf",
  number =		 "6",
  pages =		 "297-310",
  crossref =		 "p11111"
}

@article{ManschitzRAL2018,
  author =		 "Manschitz, S. and  Gienger, M. and  Kober, J. and  Peters, J.",
  year =		 "2018",
  title =		 "Mixture of Attractors: A novel Movement Primitive Representation for Learning Motor Skills from Demonstrations",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/SimonManschitz/ManschitzRAL2018.pdf",
  number =		 "2",
  pages =		 "926-933",
  crossref =		 "p11113"
}

@inproceedings{lioutikov_movement_pcfg_icra2018,
  author =		 "Lioutikov, R. and  Maeda, G. and  Veiga, F.F. and  Kersting, K. and  Peters, J.",
  year =		 "2018",
  title =		 "Inducing Probabilistic Context-Free Grammars for the Sequencing of Robot Movement Primitives",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "3rd-hand",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/RudolfLioutikov/lioutikov_movement_pcfg_icra2018.pdf",
  crossref =		 "p11116"
}

@inproceedings{LearningRobustPoliciesForObjectManipulationWithRobotSwarms,
  author =		 "Gebhardt, G.H.W. and  Daun, K. and  Schnaubelt, M. and  Neumann, G.",
  year =		 "2018",
  title =		 "Learning Robust Policies for Object Manipulation with Robot Swarms",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "swarm robotics, policy search, kernel methods, kilobots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/GregorGebhardt/LearningRobustPoliciesForObjectManipulationWithRobotSwarms.pdf",
  crossref =		 "p11126"
}

@article{NQVI_RAL_manuscript,
  author =		 "Vinogradska, J. and  Bischoff, B. and  Peters, J.",
  year =		 "2018",
  title =		 "Approximate Value Iteration based on Numerical Quadrature",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation, and IEEE Robotics and Automation Letters (RA-L)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NQVI_RAL_manuscript.pdf",
  pages =		 "1330-1337",
  crossref =		 "p11118"
}

@inproceedings{icra18_robert,
  author =		 "Pinsler, R. and  Akrour, R. and  Osa, T. and  Peters, J. and  Neumann, G.",
  year =		 "2018",
  title =		 "Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "ias",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/RiadAkrour/icra18_robert.pdf",
  crossref =		 "p11125"
}

@inproceedings{cfim_final,
  author =		 "Koert, D. and  Maeda, G. and  Neumann, G. and  Peters, J.",
  year =		 "2018",
  title =		 "Learning Coupled Forward-Inverse Models with Combined Prediction Errors",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "3rd-hand,skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/DorotheaKoert/cfim_final.pdf",
  crossref =		 "p11131"
}

@article{1811,
  author =		 "Osa, T. and  Pajarinen, J. and  Neumann, G. and  Bagnell, J.A. and  Abbeel, P. and  Peters, J.",
  year =		 "2018",
  title =		 "An Algorithmic Perspective on Imitation Learning",
  booktitle =		 "Foundations and Trends in Robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/1811.06711",
  crossref =		 "p11142"
}

@article{veigaToH2018,
  author =		 "Veiga, F. and  Peters, J. and  Hermans, T.",
  year =		 "2018",
  title =		 "Grip Stabilization of Novel Objects using Slip Prediction",
  booktitle =		 "IEEE Transactions on Haptics",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/veigaToH2018.pdf",
  number =		 "4",
  pages =		 "531--542",
  crossref =		 "p11143"
}

@article{Online_optimal_trajectory_generation,
  author =		 "Koc, O. and  Maeda, G. and  Peters, J.",
  year =		 "2018",
  title =		 "Online optimal trajectory generation for robot table tennis",
  booktitle =		 "Robotics and Autonomous Systems (RAS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Online_optimal_trajectory_generation.pdf",
  crossref =		 "p11144"
}

@article{fnbot1200024,
  author =		 "Ewerton, M. and  Rother, D. and  Weimar, J. and  Kollegger, G. and  Wiemeyer, J. and  Peters, J. and  Maeda, G.",
  year =		 "2018",
  title =		 "Assisting Movement Training and Execution with Visual and Haptic Feedback",
  booktitle =		 "Frontiers in Neurorobotics",
  key =			 "3rd-hand, bimrob, romans, skills4robots, nedo",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/fnbot-12-00024.pdf",
  crossref =		 "p11145"
}

@inproceedings{maxent18_belousov,
  author =		 "Belousov, B. and  Peters, J.",
  year =		 "2018",
  title =		 "Entropic Regularization of Markov Decision Processes",
  booktitle =		 "38th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering",
  key =			 "reinforcement learning and  actor-critic methods and  entropic proximal mappings and  policy search",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/maxent18_belousov.pdf",
  crossref =		 "p11189"
}

@inproceedings{Parmas_PICML_2018,
  author =		 "Parmas, P. and  Doya, K. and  Rasmussen, C. and  Peters, J.",
  year =		 "2018",
  title =		 "PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  crossref =		 "p11146"
}

@inproceedings{VIPS_full,
  author =		 "Arenz, O. and  Zhong, M. and  Neumann, G.",
  year =		 "2018",
  title =		 "Efficient Gradient-Free Variational Inference using Policy Search",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  key =			 "variational inference, policy search, sampling",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/OlegArenz/VIPS_full.pdf",
  publisher =		 "pmlr",
  pages =		 "234--243",
  crossref =		 "p11147"
}

@article{RAL18final,
  author =		 "Buechler, D. and  Calandra, R. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2018",
  title =		 "Control of Musculoskeletal Systems using Learned Dynamics Models",
  booktitle =		 "IEEE Robotics and Automation Letters, and IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://ei.is.tuebingen.mpg.de/uploads_file/attachment/attachment/422/RAL18final.pdf",
  crossref =		 "p11149"
}

@article{Sosic_JMLR_2018,
  author =		 "Sosic, A. and  Rueckert, E. and  Peters, J. and  Zoubir, A.M. and  Koeppl, H",
  year =		 "2018",
  title =		 "Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  number =		 "69",
  pages =		 "1--45",
  crossref =		 "p11154"
}

@inproceedings{iros18_riad,
  author =		 "Akrour, R. and  Veiga, F. and  Peters, J. and  Neumann, G.",
  year =		 "2018",
  title =		 "Regularizing Reinforcement Learning with State Abstraction",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/RiadAkrour/iros18_riad.pdf",
  crossref =		 "p11155"
}

@inproceedings{VALID2018Gondaliya,
  author =		 "Gondaliya, K.D. and  Peters, J. and  Rueckert, E.",
  year =		 "2018",
  title =		 "Learning to Categorize Bug Reports with LSTM Networks",
  booktitle =		 "Proceedings of the International Conference on Advances in System Testing and Validation Lifecycle",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/VALID2018Gondaliya.pdf",
  crossref =		 "p11156"
}

@article{advanced_roboitcs_18osa,
  author =		 "Osa, T. and  Peters, J. and  Neumann, G.",
  year =		 "2018",
  title =		 "Hierarchical Reinforcement Learning of Multiple Grasping Strategies with Human Instructions",
  booktitle =		 "Advanced Robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/advanced_roboitcs_18osa.pdf",
  number =		 "18",
  pages =		 "955-968",
  crossref =		 "p11157"
}

@inproceedings{Muratore_Treede_Gienger_PetersSPOTA_CoRL2018,
  author =		 "Muratore, F. and  Treede, F. and  Gienger, M. and  Peters, J.",
  year =		 "2018",
  title =		 "Domain Randomization for Simulation-Based Policy Optimization with Transferability Assessment",
  booktitle =		 "Conference on Robot Learning (CoRL)",
  key =			 "domain randomization, simulation optimization, sim-2-real",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/FabioMuratore/Muratore_Treede_Gienger_Peters--SPOTA_CoRL2018.pdf",
  crossref =		 "p11159"
}

@inproceedings{incremental_promp_2018,
  author =		 "Koert, D. and  Trick, S. and  Ewerton, M. and  Lutter, M. and  Peters, J.",
  year =		 "2018",
  title =		 "Online Learning of an Open-Ended Skill Library for Collaborative Tasks",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "skills4robots, kobo",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/DorotheaKoert/incremental_promp_2018.pdf",
  crossref =		 "p11160"
}

@inproceedings{ewrl18_riad,
  author =		 "Akrour, R. and  Peters, J. and  Neumann, G.",
  year =		 "2018",
  title =		 "Constraint-Space Projection Direct Policy Search",
  booktitle =		 "European Workshops on Reinforcement Learning (EWRL)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/RiadAkrour/ewrl18_riad.pdf",
  crossref =		 "p11161"
}

@inproceedings{pomdp_user_interaction_2018,
  author =		 "Hoelscher, J. and  Koert, D. and  Peters, J. and  Pajarinen, J.",
  year =		 "2018",
  title =		 "Utilizing Human Feedback in POMDP Execution and Specification",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "romans,skills4robots,roboleap",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/DorotheaKoert/pomdp_user_interaction_2018.pdf",
  crossref =		 "p11162"
}

@inproceedings{ewrl18_belousov,
  author =		 "Belousov, B. and  Peters, J.",
  year =		 "2018",
  title =		 "Mean Squared Advantage Minimization as a Consequence of Entropic Policy Improvement Regularization",
  booktitle =		 "European Workshops on Reinforcement Learning (EWRL)",
  key =			 "policy optimization, entropic proximal mappings, actor-critic algorithms",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/BorisBelousov/ewrl18_belousov.pdf",
  crossref =		 "p11164"
}

@unpublished{PinslerEtAl_ICRA2018swarms,
  author =		 "Pinsler, R. and  Maag, M. and  Arenz, O. and  Neumann, G.",
  year =		 "2018",
  title =		 "Inverse Reinforcement Learning of Bird Flocking Behavior",
  booktitle =		 "Swarms: From Biology to Robotics and Back (ICRA Workshop)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/OlegArenz/PinslerEtAl_ICRA2018swarms.pdf",
  crossref =		 "p11210"
}

@article{Kupcsik_AIJ_2015,
  author =		 "Kupcsik, A.G. and  Deisenroth, M.P. and  Peters, J. and  Ai Poh, L. and  Vadakkepat, V. and  Neumann, G.",
  year =		 "2017",
  title =		 "Model-based Contextual Policy Search for Data-Efficient Generalization of Robot Skills",
  booktitle =		 "Artificial Intelligence",
  key =			 "complacs",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Kupcsik_AIJ_2015.pdf",
  pages =		 "415-439",
  crossref =		 "p10684"
}

@article{Anticipatory_Action_Selection,
  author =		 "Wang, Z. and  Boularias, A. and  Muelling, K. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2017",
  title =		 "Anticipatory Action Selection for Human-Robot Table Tennis",
  booktitle =		 "Artificial Intelligence",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Anticipatory_Action_Selection.pdf",
  pages =		 "399-414",
  crossref =		 "p10784"
}

@article{gjm_2016_AURO_c,
  author =		 "Maeda, G. and  Neumann, G. and  Ewerton, M. and  Lioutikov, R. and  Kroemer, O. and  Peters, J.",
  year =		 "2017",
  title =		 "Probabilistic Movement Primitives for Coordination of Multiple Human-Robot Collaborative Tasks",
  booktitle =		 "Autonomous Robots (AURO)",
  key =			 "3rd-hand, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/PubGJMaeda/gjm_2016_AURO_c.pdf",
  number =		 "3",
  pages =		 "593-612",
  crossref =		 "p10934"
}

@article{parisi_neurocomp_morl,
  author =		 "Parisi, S. and  Pirotta, M. and  Peters, J.",
  year =		 "2017",
  title =		 "Manifold-based Multi-objective Policy Search with Sample Reuse",
  booktitle =		 "Neurocomputing",
  key =			 "multi-objective, reinforcement learning, policy search, black-box optimization, importance sampling",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/parisi_neurocomp_morl.pdf",
  pages =		 "3-14",
  crossref =		 "p10961"
}

@inbook{Peters_SHRE_2017,
  author =		 "Peters, J. and  Lee, D. and  Kober, J. and  Nguyen-Tuong, D. and  Bagnell, J. and  Schaal, S.",
  year =		 "2017",
  title =		 "Chapter 15: Robot Learning",
  booktitle =		 "Springer Handbook of Robotics, 2nd Edition",
  publisher =		 "springer international publishing",
  pages =		 "357-394",
  crossref =		 "p10962"
}

@article{phase_estim_IJRR,
  author =		 "Maeda, G. and  Ewerton, M. and  Neumann, G. and  Lioutikov, R. and  Peters, J.",
  year =		 "2017",
  title =		 "Phase Estimation for Fast Action Recognition and Trajectory Generation in Human-Robot Collaboration",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  key =			 "3rd-hand, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/PubGJMaeda/phase_estim_IJRR.pdf",
  number =		 "13-14",
  pages =		 "1579-1594",
  crossref =		 "p10985"
}

@article{ias_padois_et_al_revised_finalised,
  author =		 "Padois, V. and  Ivaldib, S. and  Babič, J. and  Mistry, M. and  Peters, J. and  Nori, F.",
  year =		 "2017",
  title =		 "Whole-body multi-contact motion in humans and humanoids",
  booktitle =		 "Robotics and Autonomous Systems",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ias_padois_et_al_revised_finalised.pdf",
  pages =		 "97-117",
  crossref =		 "p10991"
}

@inproceedings{tangkaratt2017policy,
  author =		 "Tangkaratt, V. and  van Hoof, H. and  Parisi, S. and  Neumann, G. and  Peters, J. and  Sugiyama, M.",
  year =		 "2017",
  title =		 "Policy Search with High-Dimensional Context Variables",
  booktitle =		 "Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/tangkaratt2017policy.pdf",
  crossref =		 "p11001"
}

@article{IJSR_edhhi,
  author =		 "Ivaldi, S. and  Lefort, S. and  Peters, J. and  Chetouani, M. and  Provasi, J. and  Zibetti, E.",
  year =		 "2017",
  title =		 "Towards Engagement Models that Consider Individual Factors in HRI: On the Relation of Extroversion and Negative Attitude Towards Robots to Gaze and Speech During a Human-Robot Assembly Task",
  booktitle =		 "International Journal of Social Robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IJSR_edhhi.pdf",
  pages =		 "63-86",
  crossref =		 "p11003"
}

@inproceedings{TheKernelKalmanRule,
  author =		 "Gebhardt, G.H.W. and  Kupcsik, A.G. and  Neumann, G.",
  year =		 "2017",
  title =		 "The Kernel Kalman Rule - Efficient Nonparametric Inference with Recursive Least Squares",
  booktitle =		 "Proceedings of the National Conference on Artificial Intelligence (AAAI)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/GregorGebhardt/TheKernelKalmanRule.pdf",
  crossref =		 "p11015"
}

@article{Yi_SAAP_2017,
  author =		 "Yi, Z. and  Zhang, Y. and  Peters, J.",
  year =		 "2017",
  title =		 "Bioinspired Tactile Sensor for Surface Roughness Discrimination",
  booktitle =		 "Sensors and Actuators A: Physical",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Bioinspired_tactile_sensor.pdf",
  pages =		 "46-53",
  crossref =		 "p11026"
}

@article{Osa_RAL_2017,
  author =		 "Osa, T. and  Ghalamzan, E. A. M. and  Stolkin, R. and  Lioutikov, R. and  Peters, J. and  Neumann, G. ",
  year =		 "2017",
  title =		 "Guiding Trajectory Optimization by Demonstrated Distributions",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Osa_RAL_2017.pdf",
  publisher =		 "ieee",
  number =		 "2",
  pages =		 "819-826",
  crossref =		 "p11027"
}

@article{Kroemer_RAL_2017,
  author =		 "Kroemer, O. and  Peters, J.",
  year =		 "2017",
  title =		 "A Comparison of Autoregressive Hidden Markov Models for Multi-Modal Manipulations with Variable Masses",
  booktitle =		 "Proceedings of the International Conference of Robotics and Automation, and IEEE Robotics and Automation Letters (RA-L)",
  key =			 "3rd-hand, tacman",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Kroemer_RAL_2017.pdf",
  number =		 "2",
  pages =		 "1101 - 1108",
  crossref =		 "p11028"
}

@inproceedings{ewerton_motorik2017,
  author =		 "Ewerton, M. and  Kollegger, G. and  Maeda, G. and  Wiemeyer, J. and  Peters, J.",
  year =		 "2017",
  title =		 "Iterative Feedback-basierte Korrekturstrategien beim Bewegungslernen von Mensch-Roboter-Dyaden",
  booktitle =		 "DVS Sportmotorik 2017",
  key =			 "bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/ewerton_motorik2017.pdf",
  crossref =		 "p11029"
}

@inproceedings{kollegger_motorik2017,
  author =		 "Kollegger, G. and  Reinhardt, N. and  Ewerton, M. and  Peters, J. and  Wiemeyer, J.",
  year =		 "2017",
  title =		 "Die Bedeutung der Beobachtungsperspektive beim Bewegungslernen von Mensch-Roboter-Dyaden",
  booktitle =		 "DVS Sportmotorik 2017",
  key =			 "bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/kollegger_motorik2017.pdf",
  crossref =		 "p11030"
}

@inproceedings{wiemeyer_motorik2017,
  author =		 "Wiemeyer, J. and  Peters, J. and  Kollegger, G. and  Ewerton, M.",
  year =		 "2017",
  title =		 "BIMROB – Bidirektionale Interaktion von Mensch und Roboter beim Bewegungslernen",
  booktitle =		 "DVS Sportmotorik 2017",
  key =			 "bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/wiemeyer_motorik2017.pdf",
  crossref =		 "p11031"
}

@inproceedings{firas_ICRA17,
  author =		 "Farraj, F. B. and  Osa, T. and  Pedemonte, N. and  Peters, J. and  Neumann, G. and  Giordano, P.R.",
  year =		 "2017",
  title =		 "A Learning-based Shared Control Architecture for Interactive Task Execution",
  booktitle =		 "Proceedings of the  IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/firas_ICRA17.pdf",
  crossref =		 "p11032"
}

@inproceedings{wilbers_icra_2017,
  author =		 "Wilbers, D. and  Lioutikov, R. and  Peters, J.",
  year =		 "2017",
  title =		 "Context-Driven Movement Primitive Adaptation",
  booktitle =		 "Proceedings of the  IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "3rd-hand",
  URL =			 "/uploads/Member/PubRudolfLioutikov/wilbers_icra_2017.pdf",
  crossref =		 "p11033"
}

@inproceedings{icra17_felix,
  author =		 "End, F. and  Akrour, R. and  Peters, J. and  Neumann, G.",
  year =		 "2017",
  title =		 "Layered Direct Policy Search for Learning Hierarchical Skills",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Research/Overview/icra17_felix.pdf",
  crossref =		 "p11034"
}

@inproceedings{icra17_alex,
  author =		 "Gabriel, A. and  Akrour, R. and  Peters, J. and  Neumann, G.",
  year =		 "2017",
  title =		 "Empowered Skills",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "ias",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Research/Overview/icra17_alex.pdf",
  crossref =		 "p11035"
}

@inproceedings{Abdulsamad_ICAPS_2017,
  author =		 "Abdulsamad, H. and  Arenz, O. and  Peters, J. and  Neumann, G.",
  year =		 "2017",
  title =		 "State-Regularized Policy Search for Linearized Dynamical Systems",
  booktitle =		 "Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Abdulsamad_ICAPS_2017.pdf",
  crossref =		 "p11043"
}

@article{lioutikov_probs_ijrr2017,
  author =		 "Lioutikov, R. and  Neumann, G. and  Maeda, G. and  Peters, J.",
  year =		 "2017",
  title =		 "Learning Movement Primitive Libraries through Probabilistic Segmentation",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  key =			 "3rd-hand",
  URL =			 "/uploads/Publications/lioutikov_probs_ijrr2017.pdf",
  number =		 "8",
  pages =		 "879-894",
  crossref =		 "p11056"
}

@inproceedings{Fiebig_PGBIC_2017,
  author =		 "Fiebig, K.H. and  Jayaram, V. and  Hesse, T. and  Blank, A. and  Peters, J. and  Grosse-Wentrup, M.",
  year =		 "2017",
  title =		 "Bayesian Regression for Artifact Correction in Electroencephalography",
  booktitle =		 "Proceedings of the 7th Graz Brain-Computer Interface Conference",
  crossref =		 "p11057"
}

@inproceedings{akrour17a,
  author =		 "Akrour, R. and  Sorokin, D. and  Peters, J. and  Neumann, G.",
  year =		 "2017",
  title =		 "Local Bayesian Optimization of Motor Skills",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  URL =			 "http://proceedings.mlr.press/v70/akrour17a/akrour17a.pdf",
  crossref =		 "p11060"
}

@inproceedings{LearningToAssembleObjectsWithARobotSwarm,
  author =		 "Gebhardt, G.H.W. and  Daun, K. and  Schnaubelt, M. and  Hendrich, A. and  Kauth, D. and  Neumann, G.",
  year =		 "2017",
  title =		 "Learning to Assemble Objects with a Robot Swarm",
  booktitle =		 "Proceedings of the International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)",
  key =			 "multi-agent learning, reinforcement learning, swarm robotics",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/GregorGebhardt/LearningToAssembleObjectsWithARobotSwarm.pdf",
  publisher =		 "international foundation for autonomous agents and multiagent systems",
  pages =		 "1547--1549",
  crossref =		 "p11063"
}

@inproceedings{kollegger_dvs_hochschultag_2017,
  author =		 "Kollegger, G. and  Ewerton, M. and  Wiemeyer, J. and  Peters, J.",
  year =		 "2017",
  title =		 "BIMROB – Bidirectional Interaction between human and robot for the learning of movements – Robot trains human – Human trains robot",
  booktitle =		 "23. Sport­wissenschaft­licher Hochschultag der dvs",
  key =			 "bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/kollegger_dvs_hochschultag_2017.pdf",
  crossref =		 "p11064"
}

@inproceedings{tosatto_icml2017,
  author =		 "Tosatto, S. and  Pirotta, M. and  D'Eramo, C and  Restelli, M.",
  year =		 "2017",
  title =		 "Boosted Fitted Q-Iteration",
  booktitle =		 "Proceedings of the International Conference of Machine Learning (ICML)",
  key =			 "bosch-forschungstiftung",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/tosatto_icml2017.pdf",
  crossref =		 "p11067"
}

@inproceedings{Belousov_ANIPS_2016,
  author =		 "Belousov, B. and  Neumann, G. and  Rothkopf, C.A. and  Peters, J.",
  year =		 "2017",
  title =		 "Catching Heuristics Are Optimal Control Policies",
  booktitle =		 "Proceedings of the Karniel Thirteenth Computational Motor Control Workshop",
  key =			 "skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Belousov_ANIPS_2016.pdf",
  crossref =		 "p11069"
}

@inproceedings{Busch_PIICIRS_2017,
  author =		 "Busch, B. and  Maeda, G. and  Mollard, Y. and  Demangeat, M. and  Lopes, M.",
  year =		 "2017",
  title =		 "Postural Optimization for an Ergonomic Human-Robot Interaction",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "3rd-hand",
  crossref =		 "p11071"
}

@inproceedings{pajarinen_iros_2017,
  author =		 "Pajarinen, J. and  Kyrki, V. and  Koval, M. and  Srinivasa, S and  Peters, J. and  Neumann, G.",
  year =		 "2017",
  title =		 "Hybrid Control Trajectory Optimization under Uncertainty",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "romans",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/pajarinen_iros_2017.pdf",
  crossref =		 "p11072"
}

@inproceedings{parisi2017iros,
  author =		 "Parisi, S. and  Ramstedt, S. and  Peters, J.",
  year =		 "2017",
  title =		 "Goal-Driven Dimensionality Reduction for Reinforcement Learning",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/parisi2017iros.pdf",
  crossref =		 "p11074"
}

@article{paraschos_prob_prio,
  author =		 "Paraschos, A. and  Lioutikov, R. and   Peters, J. and  Neumann, G.",
  year =		 "2017",
  title =		 "Probabilistic Prioritization of Movement Primitives",
  booktitle =		 "Proceedings of the International Conference on Intelligent Robot Systems, and IEEE Robotics and Automation Letters (RA-L)",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/AlexandrosParaschos/paraschos_prob_prio.pdf",
  crossref =		 "p11075"
}

@article{vanHoof_MLJ_2017,
  author =		 "van Hoof, H. and  Tanneberg, D. and  Peters, J.",
  year =		 "2017",
  title =		 "Generalized Exploration in Policy Search",
  booktitle =		 "Machine Learning (MLJ)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/vanHoof_MLJ_2017.pdf",
  number =		 "9-10",
  pages =		 "1705-1724",
  crossref =		 "p11078"
}

@article{vanHoof_JMLR_2017,
  author =		 "van Hoof, H. and  Neumann, G. and  Peters, J.",
  year =		 "2017",
  title =		 "Non-parametric Policy Search with Limited Information Loss",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  key =			 "tacman, reinforcement learning",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Alumni/HerkeVanHoof/vanHoof_JMLR_2017.pdf",
  number =		 "73",
  pages =		 "1-46",
  crossref =		 "p11080"
}

@article{16590,
  author =		 "Vinogradska, J. and  Bischoff, B. and  Nguyen-Tuong, D. and  Peters, J.",
  year =		 "2017",
  title =		 "Stability of Controllers for Gaussian Process Forward Models",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/16-590.pdf",
  number =		 "100",
  pages =		 "1-37",
  crossref =		 "p11082"
}

@article{Dermy_FRA_2017,
  author =		 "Dermy, O. and  Paraschos, A. and  Ewerton, M. and  Charpillet, F. and  Peters, J. and  Ivaldi, S",
  year =		 "2017",
  title =		 "Prediction of intention during interaction with iCub with Probabilistic Movement Primitives",
  booktitle =		 "Frontiers in Robotics and AI",
  key =			 "codyco, bimrob",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/frobt-04-00045.pdf",
  pages =		 "45",
  crossref =		 "p11084"
}

@misc{WORKSHOP_IROS_2017,
  author =		 "Ewerton, M. and  Maeda, G. and  Rother, D. and  Weimar, J. and  Lotter, L. and  Kollegger, G. and  Wiemeyer, J. and  Peters, J.",
  year =		 "2017",
  title =		 "Assisting the practice of motor skills by humans with a probability distribution over trajectories",
  booktitle =		 "Workshop Human-in-the-loop robotic manipulation: on the influence of the human role at IROS 2017,  Vancouver, Canada",
  key =			 "3rd-hand, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Member/PubMarcoEwerton/WORKSHOP_IROS_2017.pdf",
  crossref =		 "p11090"
}

@inproceedings{corl17_01,
  author =		 "Tanneberg, D. and  Peters, J. and  Rueckert, E.",
  year =		 "2017",
  title =		 "Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals",
  booktitle =		 "Proceedings of the Conference on Robot Learning (CoRL)",
  key =			 "goal-robots, skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/DanielTanneberg/corl17_01.pdf",
  crossref =		 "p11088"
}

@inproceedings{maedaCoRL_20171014,
  author =		 "Maeda, G. and  Ewerton, M. and  Osa, T. and  Busch, B. and  Peters, J.",
  year =		 "2017",
  title =		 "Active Incremental Learning of Robot Movement Primitives",
  booktitle =		 "Proceedings of the Conference on Robot Learning (CoRL)",
  key =			 "3rd-hand, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/PubGJMaeda/maedaCoRL_20171014.pdf",
  crossref =		 "p11089"
}

@inproceedings{Humanoids2017Rueckert,
  author =		 "Rueckert, E. and  Nakatenus, M. and  Tosatto, S. and  Peters, J.",
  year =		 "2017",
  title =		 "Learning Inverse Dynamics Models in O(n) time with LSTM networks",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "goal-robots, skills4robots, bosch-forschungstiftung",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Humanoids2017Rueckert.pdf",
  crossref =		 "p11091"
}

@inproceedings{humanoids17_01,
  author =		 "Tanneberg, D. and  Peters, J. and  Rueckert, E.",
  year =		 "2017",
  title =		 "Efficient Online Adaptation with Stochastic Recurrent Neural Networks",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "goal-robots, skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/DanielTanneberg/humanoids17_01.pdf",
  crossref =		 "p11092"
}

@inproceedings{stark_humanoids2017,
  author =		 "Stark, S. and  Peters, J. and  Rueckert, E.",
  year =		 "2017",
  title =		 "A Comparison of Distance Measures for Learning Nonparametric Motor Skill Libraries",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "goal-robots, skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/SvenjaStark/stark_humanoids2017.pdf",
  crossref =		 "p11093"
}

@article{Kollegger_PISCSS_2017,
  author =		 "Kollegger, G. and  Ewerton, M. and  Wiemeyer, J. and  Peters, J.",
  year =		 "2017",
  title =		 "BIMROB -- Bidirectional Interaction Between Human and Robot for the Learning of Movements",
  booktitle =		 "Proceedings of the 11th International Symposium on Computer Science in Sport (IACSS 2017)",
  key =			 "bimrob",
  URL =			 "https://doi.org/10.1007/978-3-319-67846-7_15",
  publisher =		 "springer international publishing",
  pages =		 "151--163",
  ISBN/ISSN =		 "978-3-319-67846-7",
  crossref =		 "p11106"
}

@inproceedings{Humanoids2017Thiem,
  author =		 "Thiem, S. and  Stark, S. and  Tanneberg, D. and  Peters, J. and  Rueckert, E.",
  year =		 "2017",
  title =		 "Simulation of the underactuated Sake Robotics Gripper in V-REP",
  booktitle =		 "Workshop at the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "goal-robots, skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/PubElmarRueckert/Humanoids2017Thiem.pdf",
  crossref =		 "p11108"
}

@inproceedings{Grossberger_PGBIC_2017,
  author =		 "Grossberger, L. and  Hohmann, M.R. and  Peters J. and  Grosse-Wentrup, M.",
  year =		 "2017",
  title =		 "Investigating Music Imagery as a Cognitive Paradigm for Low-Cost Brain-Computer Interfaces",
  booktitle =		 "Proceedings of the 7th Graz Brain-Computer Interface Conference",
  crossref =		 "p11124"
}

@inproceedings{Kollegger_ITSSHVS_2017,
  author =		 "Kollegger, G., Wiemeyer, J., Ewerton, M. & Peters, J.",
  year =		 "2017",
  title =		 "BIMROB - Bidirectional Interaction between human and robot for the learning of movements - Robot trains human - Human trains robot",
  booktitle =		 "Inovation & Technologie im Sport - 23. Sportwissenschaftlicher Hochschultag der deutschen Vereinigung für Sportwissenschaft",
  key =			 "bimrob",
  publisher =		 "czwalina-feldhaus",
  pages =		 "179",
  crossref =		 "p11133"
}

@techreport{180100056,
  author =		 "Belousov, B. and  Peters, J.",
  year =		 "2017",
  title =		 "f-Divergence Constrained Policy Improvement",
  booktitle =		 "arXiv",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/1801.00056.pdf",
  crossref =		 "p11135"
}

@inproceedings{osa_ISER2016,
  author =		 "Osa, T. and  Peters, J. and  Neumann, G.",
  year =		 "2016",
  title =		 "Experiments with Hierarchical Reinforcement Learning of Multiple Grasping Policies",
  booktitle =		 "Proceedings of the International Symposium on Experimental Robotics (ISER)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/osa_ISER2016.pdf",
  crossref =		 "p10950"
}

@inproceedings{OCandIOCByMatchingDistributions_withSupplements,
  author =		 "Arenz, O. and  Abdulsamad, H. and  Neumann, G.",
  year =		 "2016",
  title =		 "Optimal Control and Inverse Optimal Control by Distribution Matching",
  booktitle =		 "Proceedings of the International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "imitation learning, inverse optimal control, optimal control",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Team/OlegArenz/OC and IOC By Matching Distributions_withSupplements.pdf",
  publisher =		 "ieee",
  crossref =		 "p10968"
}

@article{srep21142,
  author =		 "Rueckert, E. and  Kappel, D. and  Tanneberg, D. and  Pecevski, D and  Peters, J.",
  year =		 "2016",
  title =		 "Recurrent Spiking Networks Solve Planning Tasks",
  booktitle =		 "Nature PG: Scientific Reports",
  key =			 "3rdhand, codyco",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/srep21142",
  publisher =		 "nature publishing group",
  number =		 "21142",
  ISBN/ISSN =		 "10.1038/srep21142",
  crossref =		 "p10897"
}

@inproceedings{KohlschuetterMEDICON_2016,
  author =		 "Kohlschuetter, J. and  Peters, J. and  Rueckert, E.",
  year =		 "2016",
  title =		 "Learning Probabilistic Features from EMG Data for Predicting Knee Abnormalities",
  booktitle =		 "Proceedings of the XIV Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON)",
  key =			 "codyco, tacman",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/KohlschuetterMEDICON_2016.pdf",
  crossref =		 "p10898"
}

@article{maeda_RAL_golf_2016,
  author =		 "Maeda, G. and  Ewerton, M. and  Koert, D and  Peters, J.",
  year =		 "2016",
  title =		 "Acquiring and Generalizing the Embodiment Mapping from Human Observations to Robot Skills",
  booktitle =		 "IEEE Robotics and Automation Letters (RA-L)",
  key =			 "3rd-hand, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/GuilhermeMaeda/maeda_RAL_golf_2016.pdf",
  number =		 "2",
  pages =		 "784--791",
  crossref =		 "p10899"
}

@inproceedings{main_revised,
  author =		 "Modugno, V. and  Neumann, G. and  Rueckert, E. and  Oriolo, G. and  Peters, J. and  Ivaldi, S.",
  year =		 "2016",
  title =		 "Learning soft task priorities for control of redundant robots",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "codyco",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/main_revised.pdf",
  crossref =		 "p10900"
}

@inproceedings{Buechler_PICRA_2016,
  author =		 "Buechler, D. and  Ott, H. and  Peters, J.",
  year =		 "2016",
  title =		 "A Lightweight Robotic Arm with Pneumatic Muscles for Robot Learning",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  crossref =		 "p10901"
}

@inproceedings{ewerton_icra_2016_stockholm,
  author =		 "Ewerton, M. and  Maeda, G. and  Neumann, G. and  Kisner, V. and  Kollegger, G. and  Wiemeyer, J. and  Peters, J.",
  year =		 "2016",
  title =		 "Movement Primitives with Multiple Phase Parameters",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "bimrob, 3rd-hand",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/ewerton_icra_2016_stockholm.pdf",
  pages =		 "201--206",
  crossref =		 "p10902"
}

@article{Daniel2016JMLR,
  author =		 "Daniel, C. and  Neumann, G. and  Kroemer, O. and  Peters, J.",
  year =		 "2016",
  title =		 "Hierarchical Relative Entropy Policy Search",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Daniel2016JMLR.pdf",
  pages =		 "1-50",
  crossref =		 "p10920"
}

@techreport{161208202,
  author =		 "Veiga, F.F. and  Peters, J.",
  year =		 "2016",
  title =		 "Can Modular Finger Control for In-Hand Object Stabilization be accomplished by Independent Tactile Feedback Control Laws?",
  booktitle =		 "arXiv",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/1612.08202.pdf",
  crossref =		 "p11045"
}

@article{contextualWalking,
  author =		 "Abdolmaleki, A. and  Lau, N. and  Reis, L. and  Peters, J. and  Neumann, G.",
  year =		 "2016",
  title =		 "Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller",
  booktitle =		 "Journal of Intelligent & Robotic Systems",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/contextualWalking.pdf",
  crossref =		 "p10935"
}

@inproceedings{Vinogradska_ICML_2016,
  author =		 "Vinogradska, J. and  Bischoff, B. and  Nguyen-Tuong, D. and  Romer, A. and  Schmidt, H. and  Peters, J.",
  year =		 "2016",
  title =		 "Stability of Controllers for Gaussian Process Forward Models",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Publications/Vinogradska_ICML_2016.pdf",
  crossref =		 "p10941"
}

@inproceedings{akrour16,
  author =		 "Akrour, R. and  Abdolmaleki, A. and  Abdulsamad, H. and  Neumann, G.",
  year =		 "2016",
  title =		 "Model-Free Trajectory Optimization for Reinforcement Learning",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/akrour16.pdf",
  crossref =		 "p10944"
}

@inproceedings{Cybathlon16_AdaptiveTrainingRL,
  author =		 "Sharma, D. and  Tanneberg, D. and  Grosse-Wentrup, M. and  Peters, J. and  Rueckert, E.",
  year =		 "2016",
  title =		 "Adaptive Training Strategies for BCIs",
  booktitle =		 "Cybathlon Symposium",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/ElmarR%c3%bcckert/Cybathlon16_AdaptiveTrainingRL.pdf",
  crossref =		 "p10952"
}

@inproceedings{1402,
  author =		 "Calandra, R. and  Peters, J. and  Rasmussen, C.E. and  Deisenroth, M.P.",
  year =		 "2016",
  title =		 "Manifold Gaussian Processes for Regression",
  booktitle =		 "Proceedings of the International Joint Conference on Neural Networks (IJCNN)",
  key =			 "codyco",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/1402.5876v4",
  crossref =		 "p10948"
}

@inproceedings{ROMANS16_daglove,
  author =		 "Weber, P. and  Rueckert, E. and  Calandra, R. and  Peters, J. and  Beckerle, P.",
  year =		 "2016",
  title =		 "A Low-cost Sensor Glove with Vibrotactile Feedback and Multiple Finger Joint and Hand Motion Sensing for Human-Robot Interaction",
  booktitle =		 "Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/ElmarR%c3%bcckert/ROMANS16_daglove.pdf",
  crossref =		 "p10949"
}

@article{srep28455,
  author =		 "Rueckert, E. and  Camernik, J. and  Peters, J. and  Babic, J.",
  year =		 "2016",
  title =		 "Probabilistic Movement Models Show that Postural Control Precedes and Predicts Volitional Motor Control",
  booktitle =		 "Nature PG: Scientific Reports",
  key =			 "codyco and  tacman",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/srep28455",
  number =		 "28455",
  crossref =		 "p10951"
}

@article{Daniel2016ECML,
  author =		 "Daniel, C. and  van Hoof, H. and  Peters, J. and  Neumann, G.",
  year =		 "2016",
  title =		 "Probabilistic Inference for Determining Options in Reinforcement Learning",
  booktitle =		 "Machine Learning (MLJ)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Daniel2016ECML.pdf",
  number =		 "2-3",
  pages =		 "337-357",
  crossref =		 "p10955"
}

@inproceedings{ManschitzIROS2016,
  author =		 "Manschitz, S. and  Gienger, M. and  Kober, J. and  Peters, J.",
  year =		 "2016",
  title =		 "Probabilistic Decomposition of Sequential Force Interaction Tasks into Movement Primitives",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "honda, hri-collaboration",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/SimonManschitz/ManschitzIROS2016.pdf",
  crossref =		 "p10956"
}

@inproceedings{hoof2016IROS,
  author =		 "van Hoof, H. and  Chen, N. and  Karl, M. and  van der Smagt, P. and  Peters, J.",
  year =		 "2016",
  title =		 "Stable Reinforcement Learning with Autoencoders for Tactile and Visual Data",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "tacman, tactile manipulation",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/hoof2016IROS.pdf",
  crossref =		 "p10957"
}

@inproceedings{iros2016yi,
  author =		 "Yi, Z. and  Calandra, R. and  Veiga, F. and  van Hoof, H. and  Hermans, T. and  Zhang, Y. and  Peters, J.",
  year =		 "2016",
  title =		 "Active Tactile Object Exploration with Gaussian Processes",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "tacman, tactile manipulation",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Publications/Other/iros2016yi.pdf",
  crossref =		 "p10958"
}

@inproceedings{Koc_PICIRS_2016,
  author =		 "Koc, O. and  Peters, J. and  Maeda, G.",
  year =		 "2016",
  title =		 "A New Trajectory Generation Framework in Robotic Table Tennis",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  crossref =		 "p10959"
}

@inproceedings{Belousov_ANIPS_2016,
  author =		 "Belousov, B. and  Neumann, G. and  Rothkopf, C. and  Peters, J.",
  year =		 "2016",
  title =		 "Catching Heuristics Are Optimal Control Policies",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  key =			 "skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Belousov_ANIPS_2016.pdf",
  crossref =		 "p10969"
}

@misc{Maeda_IWHRGI_2016,
  author =		 "Maeda, G. and   Maloo, A. and  Ewerton, M. and   Lioutikov, R. and  Peters, J.",
  year =		 "2016",
  title =		 "Proactive Human-Robot Collaboration with Interaction Primitives",
  booktitle =		 "International Workshop on Human-Friendly Robotics (HFR), Genoa, Italy",
  key =			 "3rd-hand, bimrob",
  crossref =		 "p10972"
}

@inproceedings{maedamaloo_AAAI_symposium,
  author =		 "Maeda, G. and  Maloo, A. and  Ewerton, M. and   Lioutikov, R. and  Peters, J.",
  year =		 "2016",
  title =		 "Anticipative Interaction Primitives for Human-Robot Collaboration",
  booktitle =		 "AAAI Fall Symposium Series. Shared Autonomy in Research and Practice, Arlington, VA, USA",
  key =			 "3rd-hand, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/PubGJMaeda/maeda-maloo_AAAI_symposium.pdf",
  crossref =		 "p10973"
}

@inbook{Peters_EMLEIA_2016,
  author =		 "Peters, J. and  Tedrake, R. and  Roy, N. and  Morimoto, J.",
  year =		 "2016",
  title =		 "Robot Learning",
  booktitle =		 "Encyclopedia of Machine Learning, 2nd Edition, Invited Article",
  crossref =		 "p10998"
}

@inproceedings{tanneberg_humanoids16,
  author =		 "Tanneberg, D. and  Paraschos, A. and  Peters, J. and  Rueckert, E.",
  year =		 "2016",
  title =		 "Deep Spiking Networks for Model-based Planning in Humanoids",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco and  tacman",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/DanielTanneberg/tanneberg_humanoids16.pdf",
  crossref =		 "p10980"
}

@inproceedings{Huang_PICHR_2016,
  author =		 "Huang, Y. and  Buechler, D. and  Koc, O. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2016",
  title =		 "Jointly Learning Trajectory Generation and Hitting Point Prediction in Robot Table Tennis",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  crossref =		 "p10981"
}

@inproceedings{Debato,
  author =		 "Koert, D. and  Maeda, G.J. and  Lioutikov, R. and  Neumann, G. and  Peters, J.",
  year =		 "2016",
  title =		 "Demonstration Based Trajectory Optimization for Generalizable Robot Motions",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "3rd-hand,skills4robots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/DorotheaKoert/Debato.pdf",
  crossref =		 "p10982"
}

@inproceedings{Gomez-Gonzalez_PICHR_2016,
  author =		 "Gomez-Gonzalez, S. and  Neumann, G. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2016",
  title =		 "Using Probabilistic Movement Primitives for Striking Movements",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  crossref =		 "p10983"
}

@inproceedings{ewerton_humanoids_2016,
  author =		 "Ewerton, M. and  Maeda, G.J. and  Kollegger, G. and  Wiemeyer, J. and  Peters, J.",
  year =		 "2016",
  title =		 "Incremental Imitation Learning of Context-Dependent Motor Skills",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "bimrob, 3rd-hand",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/ewerton_humanoids_2016.pdf",
  pages =		 "351--358",
  crossref =		 "p10984"
}

@inproceedings{Humanoids2016Azad,
  author =		 "Azad, M. and  Ortenzi, V. and  Lin, H., C. and  Rueckert, E. and  Mistry, M.",
  year =		 "2016",
  title =		 "Model Estimation and Control of Complaint Contact Normal Force",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Humanoids2016Azad.pdf",
  crossref =		 "p10986"
}

@inproceedings{Abstracts,
  author =		 "Kollegger, G. and  Ewerton, M. and  Peters, J. and  Wiemeyer, J.",
  year =		 "2016",
  title =		 "Bidirektionale Interaktion zwischen Mensch und Roboter beim Bewegungslernen (BIMROB)",
  booktitle =		 "11. Symposium der DVS Sportinformatik",
  key =			 "bimrob",
  URL =			 "http://www.sportinformatik2016.ovgu.de/Tagung/Abstracts.html",
  crossref =		 "p10988"
}

@inproceedings{parisi2016local,
  author =		 "Parisi, S and  Blank, A and  Viernickel T and  Peters, J",
  year =		 "2016",
  title =		 "Local-utopia Policy Selection for Multi-objective Reinforcement Learning",
  booktitle =		 "Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/parisi2016local.pdf",
  crossref =		 "p10989"
}

@inbook{Peters_EMLEIA_2016,
  author =		 "Peters, J. and  Bagnell, J.A.",
  year =		 "2016",
  title =		 "Policy gradient methods",
  booktitle =		 "Encyclopedia of Machine Learning, 2nd Edition, Invited Article",
  crossref =		 "p10999"
}

@inproceedings{smc_2016_FiJaPeGW_mtl_logreg_v2,
  author =		 "Fiebig, K.-H. and  Jayaram, V. and  Peters, J. and  Grosse-Wentrup, M.",
  year =		 "2016",
  title =		 "Multi-Task Logistic Regression in Brain-Computer Interfaces",
  booktitle =		 "IEEE SMC 2016 — 6th Workshop on Brain-Machine Interface Systems",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/smc_2016_FiJaPeGW_mtl_logreg_v2.pdf",
  crossref =		 "p11000"
}

@article{Yi_PICBE_2016,
  author =		 "Yi, Z. and  Zhang, Y. and  Peters, J.",
  year =		 "2016",
  title =		 "Surface Roughness Discrimination Using Bioinspired Tactile Sensors",
  booktitle =		 "Proceedings of the 16th International Conference on Biomedical Engineering",
  crossref =		 "p11040"
}

@unpublished{arenz_workshop_IROS16,
  author =		 "Arenz, O. and  Neumann, G.",
  year =		 "2016",
  title =		 "Iterative Cost Learning from Different Types of Human Feedback",
  booktitle =		 "IROS 2016 Workshop on Human-Robot Collaboration",
  key =			 "inverse reinforcement learning, preference learning",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/arenz_workshop_IROS16.pdf",
  crossref =		 "p11136"
}

@unpublished{oleg_dgr_2016,
  author =		 "Arenz, O. and  Abdulsamad, H. and  Neumann, G.",
  year =		 "2016",
  title =		 "(Inverse) Optimal Control for Matching Higher-Order Moments",
  booktitle =		 "DGR Days (Leipzig)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/OlegArenz/oleg_dgr_2016.pdf",
  crossref =		 "p11370"
}

@article{Calandra2015a,
  author =		 "Calandra, R. and  Seyfarth, A. and  Peters, J. and  Deisenroth, M.",
  year =		 "2015",
  title =		 "Bayesian Optimization for Learning Gaits under Uncertainty",
  booktitle =		 "Annals of  Mathematics and Artificial Intelligence (AMAI)",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Calandra2015a.pdf",
  crossref =		 "p10826"
}

@article{Developing_biorobotics_for_veterinary_research,
  author =		 "Mariti, C. and  Muscolo, G.G. and  Peters, J. and  Puig, D. and  Recchiuto, C.T. and  Sighieri, C. and  Solanas, A. and  von Stryk, O.",
  year =		 "2015",
  title =		 "Developing biorobotics for veterinary research into cat movements",
  booktitle =		 "Journal of Veterinary Behavior: Clinical Applications and Research",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Developing_biorobotics_for_veterinary_research.pdf",
  pages =		 "248-254",
  crossref =		 "p10792"
}

@inproceedings{hoof2015learning,
  author =		 "van Hoof, H. and  Peters, J. and  Neumann, G.",
  year =		 "2015",
  title =		 "Learning of Non-Parametric Control Policies with High-Dimensional State Features",
  booktitle =		 "Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)",
  key =			 "tacman",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/hoof2015learning.pdf",
  crossref =		 "p10793"
}

@inproceedings{Calandra_ICRA15,
  author =		 "Calandra, R. and  Ivaldi, S. and  Deisenroth, M. and Rueckert, E. and  Peters, J.",
  year =		 "2015",
  title =		 "Learning Inverse Dynamics Models with Contacts",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Calandra_ICRA15.pdf",
  crossref =		 "p10794"
}

@inproceedings{KroemerICRA15,
  author =		 "Kroemer, O. and  Daniel, C. and  Neumann, G and  van Hoof, H. and  Peters, J.",
  year =		 "2015",
  title =		 "Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "3rd-hand, 3rdhand",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/KroemerICRA15.pdf",
  crossref =		 "p10795"
}

@inproceedings{Rueckert_ICRA14LMProMPsFinal,
  author =		 "Rueckert, E. and  Mundo, J. and  Paraschos, A. and  Peters, J. and  Neumann, G.",
  year =		 "2015",
  title =		 "Extracting Low-Dimensional Control Variables for Movement Primitives",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "3rdhand, codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Rueckert_ICRA14LMProMPsFinal.pdf",
  crossref =		 "p10796"
}

@inproceedings{ewerton_icra_2015_seattle,
  author =		 "Ewerton, M. and  Neumann, G. and  Lioutikov, R. and  Ben Amor, H. and  Peters, J. and  Maeda, G.",
  year =		 "2015",
  title =		 "Learning Multiple Collaborative Tasks with a Mixture of Interaction Primitives",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "3rd-hand, complacs, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/ewerton_icra_2015_seattle.pdf",
  pages =		 "1535--1542",
  crossref =		 "p10797"
}

@inproceedings{ICRA15_2129_FI,
  author =		 "Traversaro, S. and  Del Prete, A. and  Ivaldi, S. and  Nori, F.",
  year =		 "2015",
  title =		 "Avoiding to rely on Inertial Parameters in Estimating Joint Torques with proximal F/T sensing",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "codyco",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICRA15_2129_FI.pdf",
  crossref =		 "p10798"
}

@inproceedings{Lopes2015CogRobFoF,
  author =		 "Lopes, M. and  Peters, J. and  Piater, J. and  Toussaint, M. and  Baisero, A. and  Busch, B. and  Erkent, O. and  Kroemer, O. and  Lioutikov, R. and  Maeda, G. and  Mollard, Y. and  Munzer, T. and  Shukla, D.",
  year =		 "2015",
  title =		 "Semi-Autonomous 3rd-Hand Robot",
  booktitle =		 "Workshop on Cognitive Robotics in Future Manufacturing Scenarios, European Robotics Forum, Vienna, Austria",
  key =			 "3rdhand",
  URL =			 "https://iis.uibk.ac.at/public/papers/Lopes-2015-CogRobFoF.pdf",
  crossref =		 "p10824"
}

@inproceedings{lioutikov_humanoids_2015,
  author =		 "Lioutikov, R. and  Neumann, G. and  Maeda, G.J. and  Peters, J.",
  year =		 "2015",
  title =		 "Probabilistic Segmentation Applied to an Assembly Task",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "3rd-hand",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/lioutikov_humanoids_2015.pdf",
  crossref =		 "p10873"
}

@inproceedings{Paraschos_IROS_2015,
  author =		 "Paraschos, A. and  Rueckert, E. and  Peters, J and  Neumann, G.",
  year =		 "2015",
  title =		 "Model-Free Probabilistic Movement Primitives for Physical Interaction",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/PubAlexParaschos/Paraschos_IROS_2015.pdf",
  crossref =		 "p10832"
}

@inproceedings{13_icra_ws_tactileforce,
  author =		 "Rueckert, E. and  Lioutikov, R. and  Calandra, R. and  Schmidt, M. and  Beckerle, P. and  Peters, J.",
  year =		 "2015",
  title =		 "Low-cost Sensor Glove with Force Feedback for Learning from Demonstrations using Probabilistic Trajectory Representations",
  booktitle =		 "ICRA 2015 Workshop on Tactile and force sensing for autonomous compliant intelligent robots",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Workshops/ICRA2015TactileForce/13_icra_ws_tactileforce.pdf",
  crossref =		 "p10831"
}

@misc{ewerton_workshop_ml_social_robotics_icra_2015,
  author =		 "Ewerton, M. and  Neumann, G. and  Lioutikov, R. and  Ben Amor, H. and  Peters, J. and  Maeda, G.",
  year =		 "2015",
  title =		 "Modeling Spatio-Temporal Variability in Human-Robot Interaction with Probabilistic Movement Primitives",
  booktitle =		 "Workshop on Machine Learning for Social Robotics, ICRA",
  key =			 "3rd-hand, complacs, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/ewerton_workshop_ml_social_robotics_icra_2015.pdf",
  crossref =		 "p10830"
}

@inproceedings{parisi_iros_2015,
  author =		 "Parisi, S. and  Abdulsamad, H. and  Paraschos, A. and  Daniel, C. and  Peters, J.",
  year =		 "2015",
  title =		 "Reinforcement Learning vs Human Programming in Tetherball Robot Games",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "scarl",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Member/PubSimoneParisi/parisi_iros_2015.pdf",
  crossref =		 "p10833"
}

@inproceedings{IROS2015veiga,
  author =		 "Veiga, F.F. and  van Hoof, H. and  Peters, J. and  Hermans, T.",
  year =		 "2015",
  title =		 "Stabilizing Novel Objects by Learning to Predict Tactile Slip",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "tacman",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/IROS2015veiga.pdf",
  crossref =		 "p10834"
}

@inproceedings{Yanlong_IROS2015,
  author =		 "Huang, Y. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2015",
  title =		 "Learning Optimal Striking Points for A Ping-Pong Playing Robot",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/YanlongHuang/Yanlong_IROS2015",
  crossref =		 "p10835"
}

@inproceedings{ManschitzIROS2015_v2,
  author =		 "Manschitz, S. and  Kober, J. and  Gienger, M. and  Peters, J.",
  year =		 "2015",
  title =		 "Probabilistic Progress Prediction and Sequencing of Concurrent Movement Primitives",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "honda",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/ManschitzIROS2015_v2.pdf",
  crossref =		 "p10836"
}

@inproceedings{ewerton_iros_2015_hamburg,
  author =		 "Ewerton, M. and  Maeda, G.J. and  Peters, J. and  Neumann, G.",
  year =		 "2015",
  title =		 "Learning Motor Skills from Partially Observed Movements Executed at Different Speeds",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "bimrob, 3rd-hand",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/MarcoEwerton/ewerton_iros_2015_hamburg.pdf",
  pages =		 "456--463",
  crossref =		 "p10837"
}

@inproceedings{Wahrburg_IROS_2015,
  author =		 "Wahrburg, A. and  Zeiss, S. and  Matthias, B. and  Peters, J. and  Ding, H.",
  year =		 "2015",
  title =		 "Combined Pose-Wrench and State Machine Representation for Modeling Robotic Assembly Skills",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "abb",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Wahrburg_IROS_2015.pdf",
  crossref =		 "p10838"
}

@article{ActiveRewardLearning,
  author =		 "Daniel, C. and  Kroemer, O. and  Viering, M. and  Metz, J. and  Peters, J.",
  year =		 "2015",
  title =		 "Active Reward Learning with a Novel Acquisition Function",
  booktitle =		 "Autonomous Robots (AURO)",
  key =			 "complacs",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/ChristianDaniel/ActiveRewardLearning.pdf",
  pages =		 "389-405",
  crossref =		 "p10840"
}

@inproceedings{Fritsche_Humanoids15,
  author =		 "Fritsche, L. and  Unverzagt, F. and  Peters, J. and  Calandra, R.",
  year =		 "2015",
  title =		 "First-Person Tele-Operation of a Humanoid Robot",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Fritsche_Humanoids15.pdf",
  crossref =		 "p10858"
}

@inproceedings{Calandra_humanoids2015,
  author =		 "Calandra, R. and  Ivaldi, S. and  Deisenroth, M. and  Peters, J.",
  year =		 "2015",
  title =		 "Learning Torque Control in Presence of Contacts using Tactile Sensing from Robot Skin",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Calandra_humanoids2015.pdf",
  crossref =		 "p10857"
}

@article{Manschitz_RAS_2015,
  author =		 "Manschitz, S. and  Kober, J. and  Gienger, M. and  Peters, J.",
  year =		 "2015",
  title =		 "Learning Movement Primitive Attractor Goals and Sequential Skills from Kinesthetic Demonstrations",
  booktitle =		 "Robotics and Autonomous Systems",
  key =			 "honda, hri-collaboration",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/ManschitzRAS2015_v2.pdf",
  pages =		 "97-107",
  ISBN/ISSN =		 "0921-8890",
  crossref =		 "p10843"
}

@inproceedings{ISRR_uploaded_20150814_small,
  author =		 "Maeda, G. and  Neumann, G. and  Ewerton, M. and  Lioutikov, R. and  Peters, J.",
  year =		 "2015",
  title =		 "A Probabilistic Framework for Semi-Autonomous Robots Based on Interaction Primitives with Phase Estimation",
  booktitle =		 "Proceedings of the International Symposium of Robotics Research (ISRR)",
  key =			 "3rd-hand, bimrob",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/PubGJMaeda/ISRR_uploaded_20150814_small.pdf",
  crossref =		 "p10853"
}

@inproceedings{Koc_PICHR_2015,
  author =		 "Koc, O. and  Maeda, G. and  Neumann, G. and  Peters, J.",
  year =		 "2015",
  title =		 "Optimizing Robot Striking Movement Primitives with Iterative Learning Control",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "3rd-hand",
  crossref =		 "p10859"
}

@inproceedings{hoelscher_ichr2015,
  author =		 "Hoelscher, J. and  Peters, J. and  Hermans, T.",
  year =		 "2015",
  title =		 "Evaluation of Interactive Object Recognition with Tactile Sensing",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "tacman, tactile manipulation",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Theses/hoelscher_ichr2015.pdf",
  crossref =		 "p10860"
}

@inproceedings{HoofHumanoids2015,
  author =		 "van Hoof, H. and  Hermans, T. and  Neumann, G. and  Peters, J.",
  year =		 "2015",
  title =		 "Learning Robot In-Hand Manipulation with Tactile Features",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "tacman, tactile manipulation",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/HoofHumanoids2015.pdf",
  crossref =		 "p10861"
}

@inproceedings{LeischnigHumanoids2015,
  author =		 "Leischnig, S. and  Luettgen, S. and  Kroemer, O. and  Peters, J. ",
  year =		 "2015",
  title =		 "A Comparison of Contact Distribution Representations for Learning to Predict Object Interactions",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "tacman, tactile manipulation",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Site/EditPublication/Leischnig-Humanoids-2015.pdf",
  crossref =		 "p10862"
}

@inproceedings{Abdolmaleki_NIPS2015,
  author =		 "Abdolmaleki, A. and   Lioutikov, R. and   Peters, J and   Lau, N. and    Reis, L. and  Neumann, G.",
  year =		 "2015",
  title =		 "Model-Based Relative Entropy Stochastic Search",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  key =			 "learnrobots",
  URL =			 "http://www.ausy.tu-darmstadt.de/uploads/Team/GerhardNeumann/Abdolmaleki_NIPS2015.pdf",
  publisher =		 "mit press",
  crossref =		 "p10870"
}

@inproceedings{Dann_PTICAPS_2015,
  author =		 "Dann, C. and  Neumann, G. and  Peters, J.",
  year =		 "2015",
  title =		 "Policy Evaluation with Temporal Differences: A Survey and Comparison",
  booktitle =		 "Proceedings of the Twenty-Fifth International Conference on Automated Planning and Scheduling (ICAPS)",
  pages =		 "359-360",
  crossref =		 "p10887"
}

@article{lioutikov_2014_itsoc,
  author =		 "Lioutikov, R. and  Paraschos, A. and  Peters, J. and  Neumann, G.",
  year =		 "2014",
  title =		 "Generalizing Movements with Information Theoretic Stochastic Optimal Control",
  booktitle =		 "Journal of Aerospace Information Systems",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/lioutikov_2014_itsoc.pdf",
  number =		 "9",
  pages =		 "579-595",
  crossref =		 "p10754"
}

@article{fncom0800062,
  author =		 "Neumann, G. and  Daniel, C. and  Paraschos, A. and  Kupcsik, A. and  Peters, J.",
  year =		 "2014",
  title =		 "Learning Modular Policies for Robotics",
  booktitle =		 "Frontiers in Computational Neuroscience",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/fncom-08-00062.pdf",
  crossref =		 "p10752"
}

@inproceedings{Nori_PWNRFIAS_2014,
  author =		 "Nori, F. and  Peters, J. and  Padois, V. and  Babic, J. and  Mistry, M. and  Ivaldi, S.",
  year =		 "2014",
  title =		 "Whole-body motion in humans and humanoids",
  booktitle =		 "Proceedings of the Workshop on New Research Frontiers for Intelligent Autonomous Systems (NRF-IAS)",
  key =			 "codyco",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/nori2014iascodyco.pdf",
  pages =		 "81-92",
  crossref =		 "p10761"
}

@article{dann14a,
  author =		 "Dann, C. and  Neumann, G. and  Peters, J.",
  year =		 "2014",
  title =		 "Policy Evaluation with Temporal Differences: A Survey and Comparison",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  key =			 "complacs",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/dann14a.pdf",
  number =		 "March",
  pages =		 "809-883",
  crossref =		 "p10643"
}

@article{Meyer_JNER_2013,
  author =		 "Meyer, T. and   Peters, J. and  Zander, T.O. and  Schoelkopf, B. and  Grosse-Wentrup, M.",
  year =		 "2014",
  title =		 "Predicting Motor Learning Performance from Electroencephalographic Data",
  booktitle =		 "Journal of Neuroengineering and Rehabilitation",
  key =			 "team athena-minerva",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Meyer_JNER_2013.pdf",
  number =		 "1",
  crossref =		 "p10649"
}

@article{Bocsi_AR_2014,
  author =		 "Bocsi, B. and  Csato, L. and  Peters, J. ",
  year =		 "2014",
  title =		 "Indirect Robot Model Learning for Tracking Control",
  booktitle =		 "Advanced Robotics",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Bocsi_AR_2014.pdf",
  crossref =		 "p10652"
}

@article{BenAmor,_AR_2014,
  author =		 "Ben Amor, H. and  Saxena, A. and  Hudson, N. and  Peters, J.",
  year =		 "2014",
  title =		 "Special issue on autonomous grasping and manipulation",
  booktitle =		 "Autonomous Robots (AURO)",
  crossref =		 "p10655"
}

@article{pami_final_w_appendix,
  author =		 "Deisenroth, M.P. and  Fox, D. and  Rasmussen, C.E.",
  year =		 "2014",
  title =		 "Gaussian Processes for Data-Efficient Learning in Robotics and Control",
  booktitle =		 "IEEE Transactions on Pattern Analysis and Machine Intelligence",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/pami_final_w_appendix.pdf",
  crossref =		 "p10656"
}

@article{wierstra14a,
  author =		 "Wierstra, D. and  Schaul, T. and  Glasmachers, T. and  Sun, Y. and  Peters, J. and  Schmidhuber, J.",
  year =		 "2014",
  title =		 "Natural Evolution Strategies",
  booktitle =		 "Journal of Machine Learning Research (JMLR)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/wierstra14a.pdf",
  number =		 "March",
  pages =		 "949-980",
  crossref =		 "p10657"
}

@inproceedings{Deisenroth_ICRA_2014,
  author =		 "Deisenroth, M.P. and  Englert, P. and  Peters, J. and  Fox, D.",
  year =		 "2014",
  title =		 "Multi-Task Policy Search for Robotics",
  booktitle =		 "Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Deisenroth_ICRA_2014.pdf",
  crossref =		 "p10658"
}

@inproceedings{Bischoff_ICRA_2014,
  author =		 "Bischoff, B. and  Nguyen-Tuong, D. and  van Hoof, H. McHutchon, A. and  Rasmussen, C.E. and  Knoll, A. and  Peters, J. and  Deisenroth, M.P.",
  year =		 "2014",
  title =		 "Policy Search For Learning Robot Control Using Sparse Data",
  booktitle =		 "Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Bischoff_ICRA_2014.pdf",
  crossref =		 "p10659"
}

@inproceedings{Calandra_ICRA2014,
  author =		 "Calandra, R. and  Seyfarth, A. and  Peters, J. and  Deisenroth, M.P.",
  year =		 "2014",
  title =		 "An Experimental Comparison of Bayesian Optimization for Bipedal Locomotion",
  booktitle =		 "Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "codyco",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/Calandra_ICRA2014.pdf",
  crossref =		 "p10660"
}

@book{Kober_STARSS_2014,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2014",
  title =		 "Learning Motor Skills - From Algorithms to Robot Experiments",
  booktitle =		 "Springer Tracts in Advanced Robotics 97 (STAR Series), Springer ",
  ISBN/ISSN =		 "978-3-319-03193-4",
  crossref =		 "p10661"
}

@inproceedings{Kroemer_ICRA_2014,
  author =		 "Kroemer, O. and  van Hoof, H. and  Neumann, G. and  Peters, J.",
  year =		 "2014",
  title =		 "Learning to Predict Phases of Manipulation Tasks as Hidden States",
  booktitle =		 "Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "tacman, 3rd-hand",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer_ICRA_2014.pdf",
  crossref =		 "p10662"
}

@inproceedings{icraHeniInteract,
  author =		 "Ben Amor, H. and  Neumann, G. and  Kamthe, S. and  Kroemer, O. and  Peters, J.",
  year =		 "2014",
  title =		 "Interaction Primitives for Human-Robot Cooperation Tasks ",
  booktitle =		 "Proceedings of 2014 IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "codyco, complacs",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/icraHeniInteract.pdf",
  crossref =		 "p10663"
}

@inproceedings{Analytic_LongTerm_Forecasting,
  author =		 "Haji Ghassemi, N. and  Deisenroth, M.P.",
  year =		 "2014",
  title =		 "Approximate Inference for Long-Term Forecasting with Periodic Gaussian Processes",
  booktitle =		 "Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Analytic_Long-Term_Forecasting.pdf",
  crossref =		 "p10665"
}

@inproceedings{Calandra_LION8,
  author =		 "Calandra, R. and  Gopalan, N. and  Seyfarth, A. and  Peters, J. and  Deisenroth, M.P.",
  year =		 "2014",
  title =		 "Bayesian Gait Optimization for Bipedal Locomotion",
  booktitle =		 "Proceedings of the 2014 Learning and Intelligent Optimization Conference (LION8)",
  key =			 "codyco",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/Calandra_LION8.pdf",
  crossref =		 "p10666"
}

@inproceedings{ICASSP_Final,
  author =		 "Kamthe, S. and  Peters, J. and  Deisenroth, M.",
  year =		 "2014",
  title =		 "Multi-modal filtering for non-linear estimation",
  booktitle =		 "Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)",
  URL =			 "https://spiral.imperial.ac.uk:8443/bitstream/10044/1/12921/2/ICASSP_Final.pdf",
  crossref =		 "p10668"
}

@inproceedings{Manschitz_PI_2014,
  author =		 "Manschitz, S. and  Kober, J. and  Gienger, M. and  Peters, J.",
  year =		 "2014",
  title =		 "Learning to Unscrew a Light Bulb from Demonstrations",
  booktitle =		 "Proceedings of ISR/ROBOTIK 2014",
  key =			 "hri-collaboration",
  crossref =		 "p10669"
}

@article{Learning_strategies_in_table_tennis_usin,
  author =		 "Muelling, K. and  Boularias, A. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2014",
  title =		 "Learning Strategies in Table Tennis using Inverse Reinforcement Learning",
  booktitle =		 "Biological Cybernetics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Research/Overview/Learning_strategies_in_table_tennis_usin.pdf",
  number =		 "5",
  pages =		 "603-619",
  crossref =		 "p10683"
}

@article{auro2013_final,
  author =		 "Saut, J.-P. and  Ivaldi, S. and  Sahbani, A. and  Bidaud, P.",
  year =		 "2014",
  title =		 "Grasping objects localized from uncertain point cloud data",
  booktitle =		 "Robotics and Autonomous Systems",
  key =			 "codyco",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/auro2013_final.pdf",
  crossref =		 "p10762"
}

@inproceedings{lioutikov_ias13_conf,
  author =		 "Lioutikov, R. and  Kroemer, O. and  Peters, J. and  Maeda, G.",
  year =		 "2014",
  title =		 "Learning Manipulation by Sequencing Motor Primitives with a Two-Armed Robot",
  booktitle =		 "Proceedings  of the 13th International Conference on Intelligent Autonomous Systems (IAS)",
  key =			 "3rd-hand",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Member/PubRudolfLioutikov/lioutikov_ias13_conf.pdf",
  crossref =		 "p10712"
}

@inproceedings{Daniel_RSS_2014,
  author =		 "Daniel, C. and  Viering, M. and  Metz, J. and  Kroemer, O. and   Peters, J.",
  year =		 "2014",
  title =		 "Active Reward Learning",
  booktitle =		 "Proceedings of Robotics: Science & Systems (R:SS)",
  key =			 "complacs",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Daniel_RSS_2014.pdf",
  crossref =		 "p10717"
}

@inproceedings{KroemerIROS2014,
  author =		 "Kroemer, O. and  Peters, J.",
  year =		 "2014",
  title =		 "Predicting Object Interactions from Contact Distributions",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "3rd-hand, tacman, codyco",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/KroemerIROS2014.pdf",
  crossref =		 "p10748"
}

@inproceedings{ChebotarIROS2014,
  author =		 "Chebotar, Y. and  Kroemer, O. and  Peters, J.",
  year =		 "2014",
  title =		 "Learning Robot Tactile Sensing for Object Manipulation",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "3rd-hand, tacman",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/ChebotarIROS2014.pdf",
  crossref =		 "p10749"
}

@inproceedings{ManschitzIROS2014,
  author =		 "Manschitz, S. and  Kober, J. and  Gienger, M. and  Peters, J.",
  year =		 "2014",
  title =		 "Learning to Sequence Movement Primitives from Demonstrations",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "hri-collaboration, honda",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/ManschitzIROS2014.pdf",
  crossref =		 "p10750"
}

@inproceedings{Luck_IROS_2014,
  author =		 "Luck, K.S. and  Neumann, G. and  Berger, E. and  Peters, J. and  Ben Amor, H.",
  year =		 "2014",
  title =		 "Latent Space Policy Search for Robotics",
  booktitle =		 "Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)",
  key =			 "complacs, codyco",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Luck_IROS_2014.pdf",
  crossref =		 "p10751"
}

@article{hoof2014probabilistic,
  author =		 "van Hoof, H. and  Kroemer, O and  Peters, J.",
  year =		 "2014",
  title =		 "Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments",
  booktitle =		 "IEEE Transactions on Robotics (TRo)",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/hoof2014probabilistic.pdf",
  number =		 "5",
  pages =		 "1198-1209",
  ISBN/ISSN =		 "1552-3098",
  crossref =		 "p10756"
}

@inproceedings{Gomez_ECML_2014,
  author =		 "Gomez, V. and   Kappen, B and  Peters, J. and   Neumann, G",
  year =		 "2014",
  title =		 "Policy Search for Path Integral Control",
  booktitle =		 "Proceedings of the European Conference on Machine Learning (ECML)",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Gomez_ECML_2014.pdf",
  crossref =		 "p10757"
}

@inproceedings{maeda2014InteractionProMP_HUMANOIDS,
  author =		 "Maeda, G.J. and  Ewerton, M. and  Lioutikov, R. and  Amor, H.B. and  Peters, J. and  Neumann, G.",
  year =		 "2014",
  title =		 "Learning Interaction for Collaborative Tasks with Probabilistic Movement Primitives",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "3rd-hand, complacs",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/PubGJMaeda/maeda2014InteractionProMP_HUMANOIDS.pdf",
  pages =		 "527--534",
  crossref =		 "p10765"
}

@inproceedings{BrandlHumanoids2014Final,
  author =		 "Brandl, S. and  Kroemer, O. and  Peters, J.",
  year =		 "2014",
  title =		 "Generalizing Pouring Actions Between Objects using Warped Parameters",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "3rd-hand",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/BrandlHumanoids2014Final.pdf",
  crossref =		 "p10766"
}

@inproceedings{Colome_Humanoids_2014,
  author =		 "Colome, A. and  Neumann, G. and  Peters, J. and  Torras, C.",
  year =		 "2014",
  title =		 "Dimensionality Reduction for Probabilistic Movement Primitives",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Colome_Humanoids_2014.pdf",
  crossref =		 "p10767"
}

@inproceedings{AICOHumanoidsFinal,
  author =		 "Rueckert, E. and  Mindt, M. and  Peters, J. and  Neumann, G.",
  year =		 "2014",
  title =		 "Robust Policy Updates for Stochastic Optimal Control",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/AICOHumanoidsFinal.pdf",
  crossref =		 "p10768"
}

@inproceedings{ivaldi2014simulators,
  author =		 "Ivaldi, S. and  Peters, J. and  Padois, V. and  Nori, F.",
  year =		 "2014",
  title =		 "Tools for simulating humanoid robot dynamics: a survey based on user feedback",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/ivaldi2014simulators.pdf",
  crossref =		 "p10769"
}

@article{Deepunsupervisednetwork_2014,
  author =		 "Droniou, A. and  Ivaldi, S. and  Sigaud, O.",
  year =		 "2014",
  title =		 "Deep unsupervised network for multimodal perception, representation and classification",
  booktitle =		 "Robotics and Autonomous Systems",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Deep unsupervised network_2014.pdf",
  crossref =		 "p10781"
}

@inproceedings{learning_tactile_manipulation_demo,
  author =		 "Hermans, T. and  Veiga, F. and  Hoelscher, J. and  van Hoof, H. and  Peters, J.",
  year =		 "2014",
  title =		 "Demonstration: Learning for Tactile Manipulation",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS/NeurIPS), Demonstration Track.",
  key =			 "tacman, tactile manipulation",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/TuckerHermans/learning_tactile_manipulation_demo.pdf",
  publisher =		 "mit press",
  crossref =		 "p10782"
}

@inproceedings{lioutikov_icra_2014,
  author =		 "Lioutikov, R. and  Paraschos, A. and  Peters, J. and  Neumann, G.",
  year =		 "2014",
  title =		 "Sample-Based Information-Theoretic Stochastic Optimal Control",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "3rd-hand",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Team/RudolfLioutikov/lioutikov_icra_2014.pdf",
  crossref =		 "p11128"
}

@article{Muelling_IJRR_2013,
  author =		 "Muelling, K. and  Kober, J. and  Kroemer, O. and  Peters, J.",
  year =		 "2013",
  title =		 "Learning to Select and Generalize Striking Movements in Robot Table Tennis",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Muelling_IJRR_2013.pdf",
  number =		 "3",
  pages =		 "263-279",
  crossref =		 "p10589"
}

@inproceedings{Daniel_ICRA_2013,
  author =		 "Daniel, C. and  Neumann, G. and  Kroemer, O. and  Peters, J.",
  year =		 "2013",
  title =		 "Learning Sequential Motor Tasks",
  booktitle =		 "Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "gert, complacs",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Daniel_ICRA_2013.pdf",
  crossref =		 "p10594"
}

@inproceedings{Englert_ICRA_2013,
  author =		 "Englert, P. and  Paraschos, A. and  Peters, J. and  Deisenroth, M. P.",
  year =		 "2013",
  title =		 "Model-based Imitation Learning by Probabilistic Trajectory Matching",
  booktitle =		 "Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Englert_ICRA_2013.pdf",
  crossref =		 "p10595"
}

@inproceedings{Gopalan_ICRA_2013,
  author =		 "Gopalan, N. and  Deisenroth, M. P. and  Peters, J.",
  year =		 "2013",
  title =		 "Feedback Error Learning for Rhythmic Motor Primitives",
  booktitle =		 "Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Gopalan_ICRA_2013.pdf",
  crossref =		 "p10596"
}

@article{Wang_IJRR_2013,
  author =		 "Wang, Z. and  Muelling, K. and  Deisenroth, M. P. and  Ben Amor, H. and  Vogt, D. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2013",
  title =		 "Probabilistic Movement Modeling for Intention Inference in Human-Robot Interaction",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Wang_IJRR_2013.pdf",
  number =		 "7",
  pages =		 "841-858",
  crossref =		 "p10598"
}

@inproceedings{peters_ECML_2013,
  author =		 "Peters, J. and  Kober, J. and  Muelling, K. and  Kroemer, O. and  Neumann, G.",
  year =		 "2013",
  title =		 "Towards Robot Skill Learning: From Simple Skills to Table Tennis",
  booktitle =		 "Proceedings of the European Conference on Machine Learning (ECML), Nectar Track",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/peters_ECML_2013.pdf",
  crossref =		 "p10626"
}

@article{Kober_IJRR_2013,
  author =		 "Kober, J. and  Bagnell, D. and  Peters, J.",
  year =		 "2013",
  title =		 "Reinforcement Learning in Robotics: A Survey",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Kober_IJRR_2013.pdf",
  number =		 "11",
  pages =		 "1238-1274",
  crossref =		 "p10613"
}

@inproceedings{Kupcsik_AAAI_2013,
  author =		 "Kupcsik, A.G. and  Deisenroth, M.P. and  Peters, J. and  Neumann, G.",
  year =		 "2013",
  title =		 "Data-Efficient Generalization of Robot Skills with Contextual Policy Search",
  booktitle =		 "Proceedings of the National Conference on Artificial Intelligence (AAAI) ",
  key =			 "gert, complacs",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Kupcsik_AAAI_2013.pdf",
  crossref =		 "p10615"
}

@inproceedings{Bocsi_IJCNN_2013,
  author =		 "Bocsi, B. and  Csato, L. and  Peters, J.",
  year =		 "2013",
  title =		 "Alignment-based Transfer Learning for Robot Models",
  booktitle =		 "Proceedings of the 2013 International Joint Conference on Neural Networks (IJCNN) ",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Bocsi_IJCNN_2013.pdf ",
  crossref =		 "p10617"
}

@inproceedings{Daniel_PIJCNN_2013,
  author =		 "Daniel, C. and  Neumann, G. and  Peters, J.",
  year =		 "2013",
  title =		 "Autonomous Reinforcement Learning with Hierarchical REPS",
  booktitle =		 "Proceedings of the 2013 International Joint Conference on Neural Networks (IJCNN) ",
  key =			 "gert, complacs",
  crossref =		 "p10618"
}

@article{Englert_ABJ_2013,
  author =		 "Englert, P. and  Paraschos, A. and  Peters, J. and Deisenroth, M.P.",
  year =		 "2013",
  title =		 "Probabilistic Model-based Imitation Learning",
  booktitle =		 "Adaptive Behavior Journal",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Englert_ABJ_2013.pdf",
  pages =		 "388-403",
  crossref =		 "p10620"
}

@inproceedings{Peters_PYLW_2013,
  author =		 "Peters, J. and  Kober, J. and  Muelling, K. and  Nguyen-Tuong, D. and  Kroemer, O.",
  year =		 "2013",
  title =		 "Learning Skills with Motor Primitives",
  booktitle =		 "Proceedings of the 16th Yale Learning Workshop",
  crossref =		 "p10621"
}

@inproceedings{Neumann_PAWIRS_2013,
  author =		 "Neumann, G. and  Kupcsik, A.G. and  Deisenroth, M.P. and  Peters, J.",
  year =		 "2013",
  title =		 "Information-Theoretic Motor Skill Learning",
  booktitle =		 "Proceedings of the AAAI 2013 Workshop on Intelligent Robotic Systems",
  key =			 "complacs",
  crossref =		 "p10622"
}

@inproceedings{iros2013Heni,
  author =		 "Ben Amor, H. and  Vogt, D. and  Ewerton, M. and  Berger, E. and  Jung, B. and  Peters, J.",
  year =		 "2013",
  title =		 "Learning Responsive Robot Behavior by Imitation",
  booktitle =		 "Proceedings of the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "codyco",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/iros2013Heni.pdf",
  crossref =		 "p10627"
}

@article{PolicySearchReview,
  author =		 "Deisenroth, M. P. and  Neumann, G. and  Peters, J.",
  year =		 "2013",
  title =		 "A Survey on Policy Search for Robotics",
  booktitle =		 "Foundations and Trends in Robotics",
  key =			 "complacs",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/PolicySearchReview.pdf",
  pages =		 "388-403",
  crossref =		 "p10628"
}

@inproceedings{hoofHUMANOIDS,
  author =		 "van Hoof, H. and  Kroemer, O and  Peters, J.",
  year =		 "2013",
  title =		 "Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered Environments ",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "gert, complacs",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/hoof-HUMANOIDS.pdf",
  crossref =		 "p10640"
}

@inproceedings{Paraschos_Humanoids_2013,
  author =		 "Paraschos, A. and  Neumann, G and  Peters, J.",
  year =		 "2013",
  title =		 "A Probabilistic Approach to Robot Trajectory Generation",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco, complacs",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Paraschos_Humanoids_2013.pdf",
  crossref =		 "p10641"
}

@inproceedings{humanoids2013Heni,
  author =		 "Berger, E. and  Vogt, D. and  Haji-Ghassemi, N. and  Jung, B. and  Ben Amor, H.",
  year =		 "2013",
  title =		 "Inferring Guidance Information in Cooperative Human-Robot Tasks",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots (HUMANOIDS)",
  key =			 "codyco",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/humanoids2013Heni.pdf",
  crossref =		 "p10642"
}

@inproceedings{Paraschos_NIPS_2013a,
  author =		 "Paraschos, A. and  Daniel, C. and  Peters, J. and  Neumann, G",
  year =		 "2013",
  title =		 "Probabilistic Movement Primitives",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS / NeurIPS)",
  key =			 "codyco, complacs",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Paraschos_NIPS_2013a.pdf",
  publisher =		 "mit press",
  crossref =		 "p10644"
}

@inbook{Sigaud_ESLSV_2012,
  author =		 "Sigaud, O. and  Peters, J.",
  year =		 "2012",
  title =		 "Robot Learning",
  booktitle =		 "Encyclopedia of the Sciences of Learning, Springer Verlag",
  URL =			 "http://dx.doi.org/10.1007/978-3-642-05181-4_1",
  publisher =		 "springer verlag",
  crossref =		 "p10321"
}

@article{rtblobjrtip2010_66510,
  author =		 "Lampert, C.H. and  Peters, J.",
  year =		 "2012",
  title =		 "Real-Time Detection of Colored Objects In Multiple Camera Streams With Off-the-Shelf Hardware Components",
  booktitle =		 "Journal of Real-Time Image Processing",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/rtblob-jrtip2010_6651[0].pdf",
  number =		 "1",
  pages =		 "31-41",
  crossref =		 "p10375"
}

@inproceedings{DanielAISTATS2012,
  author =		 "Daniel, C. and  Neumann, G. and  Peters, J.",
  year =		 "2012",
  title =		 "Hierarchical Relative Entropy Policy Search",
  booktitle =		 "Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS 2012)",
  key =			 "gert, complacs",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Member/ChristianDaniel/DanielAISTATS2012.pdf",
  crossref =		 "p10509"
}

@article{Deisenroth_ITAC_2012,
  author =		 "Deisenroth, M.P. and  Turner, R. and  Huber, M. and  Hanebeck, U.D. and  Rasmussen, C.E",
  year =		 "2012",
  title =		 "Robust Filtering and Smoothing with Gaussian Processes",
  booktitle =		 "IEEE Transactions on Automatic Control",
  key =			 "gaussian process, filtering, smoothing",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/deisenroth_IEEE-TAC2012.pdf",
  crossref =		 "p10510"
}

@inproceedings{Kroemer_ICRA_2012,
  author =		 "Kroemer, O. and  Ugur, E. and  Oztop, E.  and  Peters,  J. ",
  year =		 "2012",
  title =		 "A Kernel-based Approach to Direct Action Perception",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer_ICRA_2012.pdf",
  crossref =		 "p10517"
}

@inproceedings{Bocsi_ICRA_2012,
  author =		 "Bocsi, B. and  Hennig, P. and  Csato, L. and  Peters, J.",
  year =		 "2012",
  title =		 "Learning Tracking Control with Forward Models",
  booktitle =		 "Proceedings of the International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Bocsi_ICRA_2012.pdf",
  crossref =		 "p10518"
}

@article{kober_auro2012,
  author =		 "Kober, J. and  Wilhelm, A. and  Oztop, E. and  Peters, J.",
  year =		 "2012",
  title =		 "Reinforcement Learning to Adjust Parametrized Motor Primitives to New Situations",
  booktitle =		 "Autonomous Robots (AURO)",
  key =			 "skill learning and  motor primitives and  reinforcement learning and  meta-parameters and  policy learning",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/kober_auro2012.pdf",
  publisher =		 "springer us",
  number =		 "4",
  pages =		 "361-379",
  ISBN/ISSN =		 "0929-5593",
  crossref =		 "p10536"
}

@article{920121,
  author =		 "Vitzthum, A. and  Ben Amor, H. and  Heumer, G. and  Jung, B.",
  year =		 "2012",
  title =		 "XSAMPL3D - An Action Description Language for the Animation of Virtual Characters",
  booktitle =		 "Journal of Virtual Reality and Broadcasting",
  URL =			 "http://www.jvrb.org/9.2012/3262/920121.pdf",
  number =		 "1",
  crossref =		 "p10539"
}

@inproceedings{Wang_RSS_2012,
  author =		 "Wang, Z. and Deisenroth, M and  Ben Amor, H. and  Vogt, D. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2012",
  title =		 "Probabilistic Modeling of Human Movements for Intention Inference",
  booktitle =		 "Proceedings of Robotics: Science and Systems (R:SS)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Wang_RSS_2012.pdf",
  crossref =		 "p10545"
}

@article{NguyenTuong_TNN_2012,
  author =		 "Nguyen-Tuong, D. and  Peters, J.",
  year =		 "2012",
  title =		 "Online Kernel-based Learning for Task-Space Tracking Robot Control",
  booktitle =		 "IEEE Transactions on Neural Networks and Learning Systems",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/NguyenTuong_TNN_2012.pdf",
  number =		 "9",
  pages =		 "1417-1425 ",
  crossref =		 "p10548"
}

@inproceedings{Deisenroth_NIPS_2012,
  author =		 "Deisenroth, M.P. and  Mohamed, S.",
  year =		 "2012",
  title =		 "Expectation Propagation in Gaussian Process Dynamical Systems",
  booktitle =		 "Advances in Neural Information Processing Systems 26 (NIPS/NeurIPS), Cambridge, MA: MIT Press.",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Deisenroth_NIPS_2012.pdf",
  publisher =		 "the mit press",
  crossref =		 "p10583"
}

@inproceedings{peters_ECAI2012,
  author =		 "Peters, J. and  Kober, J. and  Muelling, K. and  Nguyen-Tuong, D. and  Kroemer, O.",
  year =		 "2012",
  title =		 "Robot Skill Learning",
  booktitle =		 "Proceedings of the European Conference on Artificial Intelligence (ECAI)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/peters_ECAI2012.pdf",
  crossref =		 "p10550"
}

@inproceedings{Boularias_ECML_2012,
  author =		 "Boularias, A. and  Kroemer, O. and  Peters, J. ",
  year =		 "2012",
  title =		 "Structured Apprenticeship Learning",
  booktitle =		 "Proceedings of the European Conference on Machine Learning (ECML)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Boularias_ECML_2012.pdf ",
  crossref =		 "p10551"
}

@inproceedings{Meyer_IROS_2012,
  author =		 "Meyer, T. and  Peters, J. and Broetz, D. and  Zander, T. and  Schoelkopf, B. and  Soekadar, S. and  Grosse-Wentrup, M.",
  year =		 "2012",
  title =		 "A Brain-Robot Interface for Studying Motor Learning after Stroke",
  booktitle =		 "Proceedings of the International Conference on Robot Systems (IROS)",
  key =			 "team athena-minerva",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Meyer_IROS_2012.pdf",
  crossref =		 "p10552"
}

@inproceedings{Deisenroth_IROS_2012,
  author =		 "Deisenroth, M.P. and  Calandra, R. and  Seyfarth, A. and  Peters, J.",
  year =		 "2012",
  title =		 "Toward Fast Policy Search for Learning Legged Locomotion",
  booktitle =		 "Proceedings of the International Conference on Robot Systems (IROS)",
  key =			 "legged locomotion, policy search, reinforcement learning, gaussian process",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Deisenroth_IROS_2012.pdf",
  crossref =		 "p10553"
}

@inproceedings{VanHoof_IROS_2012,
  author =		 "van Hoof, H. and  Kroemer, O. and Ben Amor, H. and  Peters, J.",
  year =		 "2012",
  title =		 "Maximally Informative Interaction Learning for Scene Exploration",
  booktitle =		 "Proceedings of the International Conference on Robot Systems (IROS)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/VanHoof_IROS_2012.pdf",
  crossref =		 "p10554"
}

@inproceedings{Daniel_IROS_2012,
  author =		 "Daniel, C. and  Neumann, G. and  Peters, J.",
  year =		 "2012",
  title =		 "Learning Concurrent Motor Skills in Versatile Solution Spaces",
  booktitle =		 "Proceedings of the International Conference on Robot Systems (IROS)",
  key =			 "gert, complacs",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Daniel_IROS_2012.pdf",
  crossref =		 "p10555"
}

@inproceedings{BenAmor_IROS_2012,
  author =		 "Ben Amor, H. and  Kroemer, O. and  Hillenbrand, U. and  Neumann, G. and  Peters, J.",
  year =		 "2012",
  title =		 "Generalization of Human Grasping for Multi-Fingered Robot Hands",
  booktitle =		 "Proceedings of the International Conference on Robot Systems (IROS)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/BenAmor_IROS_2012.pdf",
  crossref =		 "p10556"
}

@inproceedings{Kober_IROS_2012,
  author =		 "Kober, J and  Muelling, K. and  Peters, J.",
  year =		 "2012",
  title =		 "Learning Throwing and Catching Skills",
  booktitle =		 "Proceedings of the International Conference on Robot Systems (IROS), Video Track",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Kober_IROS_2012.pdf",
  crossref =		 "p10557"
}

@inproceedings{Deisenroth_EWRL_2012,
  author =		 "Deisenroth, M.P. and  Peters, J.",
  year =		 "2012",
  title =		 "Solving Nonlinear Continuous State-Action-Observation POMDPs for Mechanical Systems with Gaussian Noise",
  booktitle =		 "Proceedings of the European Workshop on Reinforcement Learning (EWRL)",
  URL =			 "http://www.ias.tu-darmstadt.de/uploads/Publications/Deisenroth_EWRL_2012.pdf",
  crossref =		 "p10559"
}

@inproceedings{aaaifss12rliht_submission_2,
  author =		 "Muelling, K. and  Kober, J. and  Kroemer, O. and  Peters, J.",
  year =		 "2012",
  title =		 "Learning to Select and Generalize Striking Movements in Robot Table Tennis",
  booktitle =		 "Proceedings of the AAAI 2012 Fall Symposium on Robots that Learn Interactively from Human Teachers",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/aaaifss12rliht_submission_2.pdf",
  crossref =		 "p10561"
}

@inproceedings{calandra_icann2012,
  author =		 "Calandra, R. and  Raiko, T. and  Deisenroth, M.P. and  Montesino Pouzols, F.",
  year =		 "2012",
  title =		 "Learning Deep Belief Networks from Non-Stationary Streams",
  booktitle =		 "International Conference on Artificial Neural Networks (ICANN)",
  key =			 "deep learning, non-stationary data",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Site/EditPublication/calandra_icann2012.pdf",
  crossref =		 "p10563"
}

@inproceedings{Meyer_ICN_2012,
  author =		 "Meyer, T. and  Peters, J. and  Broetz, D. and  Zander, T. and  Schoelkopf, B. and  Soekadar, S. and  Grosse-Wentrup, M.",
  year =		 "2012",
  title =		 "Investigating the Neural Basis for Stroke Rehabilitation by Brain-Computer Interfaces",
  booktitle =		 "International Conference on Neurorehabilitation",
  key =			 "team athena-minerva",
  crossref =		 "p10580"
}

@inproceedings{Kroemer_Humanoids_2012,
  author =		 "Kroemer, O. and  Ben Amor, H. and  Ewerton, M. and  Peters, J.",
  year =		 "2012",
  title =		 "Point Cloud Completion Using Extrusions",
  booktitle =		 "Proceedings of the International Conference on Humanoid Robots  (HUMANOIDS)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer_Humanoids_2012.pdf",
  crossref =		 "p10581"
}

@inproceedings{Boularias_NIPS_2012,
  author =		 "Boularias, A. and  Kroemer, O. and  Peters, J.",
  year =		 "2012",
  title =		 "Algorithms for Learning Markov Field Policies",
  booktitle =		 "Advances in Neural Information Processing Systems 26 (NIPS/NeurIPS), Cambridge, MA: MIT Press.",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Boularias_NIPS_2012.pdf",
  publisher =		 "mit press",
  crossref =		 "p10582"
}

@book{Deisenroth_EWRLproceedings_2012,
  author =		 "Deisenroth M. P. and  Szepesvari C. and  Peters J.",
  year =		 "2012",
  booktitle =		 "Proceedings of the 10th European Workshop on Reinforcement Learning",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Deisenroth_EWRLproceedings_2012.pdf",
  crossref =		 "p10597"
}

@article{Piater_IJRR_2010,
  author =		 "Piater, J. and  Jodogne, S. and  Detry, R. and  Kraft, D. and   Krueger, N. and  Kroemer, O. and  Peters, J.",
  year =		 "2011",
  title =		 "Learning Visual Representations for Perception-Action Systems",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Piater_IJRR_2010.pdf",
  number =		 "3",
  pages =		 "294-307",
  crossref =		 "p10352"
}

@article{Detry_PJBR_2011,
  author =		 "Detry, R. and  Kraft, D. and  Kroemer, O. and  Peters, J. and   Krueger, N. and   Piater, J. and ",
  year =		 "2011",
  title =		 "Learning Grasp Affordance Densities",
  booktitle =		 "Paladyn Journal of Behavioral Robotics",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Detry_PJBR_2011.pdf",
  number =		 "1",
  pages =		 "1-17",
  crossref =		 "p10353"
}

@article{kober_MACH_2011,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2011",
  title =		 "Policy Search for Motor Primitives in Robotics",
  booktitle =		 "Machine Learning (MLJ)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/kober_MACH_2011.pdf",
  number =		 "1-2",
  pages =		 "171-203",
  crossref =		 "p10355"
}

@article{Nguyen_NEURO_2011,
  author =		 "Nguyen Tuong, D. and  Peters, J.",
  year =		 "2011",
  title =		 "Incremental Sparsification for Real-time Online Model Learning",
  booktitle =		 "Neurocomputing",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Nguyen_NEURO_2011.pdf",
  number =		 "11",
  pages =		 "1859-1867",
  crossref =		 "p10356"
}

@article{GomezRodriguezJNE2011,
  author =		 "Gomez Rodriguez, M. and  Peters, J. and  Hill, J. and  Schoelkopf, B. and  Gharabaghi, A. and  Grosse-Wentrup, M.",
  year =		 "2011",
  title =		 "Closing the Sensorimotor Loop: Haptic Feedback Helps Decoding of Motor Imagery",
  booktitle =		 "Journal of Neuroengineering",
  key =			 "team athena-minerva",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Gomez-RodriguezJNE2011.pdf",
  number =		 "3",
  crossref =		 "p10451"
}

@inproceedings{Lampariello_ICRA_2011,
  author =		 "Lampariello, R. and  Nguyen Tuong, D. and  Castellini, C. and  Hirzinger, G. and  Peters, J.",
  year =		 "2011",
  title =		 "Energy-optimal robot catching in real-time",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Lampariello_ICRA_2011.pdf",
  crossref =		 "p10398"
}

@inproceedings{Kroemer_ICRA_2011,
  author =		 "Kroemer, O. and  Peters, J. ",
  year =		 "2011",
  title =		 "A Flexible Hybrid Framework for Modeling Complex Manipulation Tasks",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer_ICRA_2011.pdf",
  crossref =		 "p10399"
}

@inproceedings{Kroemer_ADPRL_2011,
  author =		 "Kroemer, O. and  Peters, J.",
  year =		 "2011",
  title =		 "Active Exploration for Robot Parameter Selection in Episodic Reinforcement Learning",
  booktitle =		 "Proceedings of the 2011 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer_ADPRL_2011.pdf",
  crossref =		 "p10402"
}

@article{Kroemer_TRo_2011,
  author =		 "Kroemer, O. and  Lampert, C.H. and  Peters, J.",
  year =		 "2011",
  title =		 "Learning Dynamic Tactile Sensing with Robust Vision-based Training",
  booktitle =		 "IEEE Transactions on Robotics (T-Ro)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer_TRo_2011.pdf",
  number =		 "3",
  pages =		 "545-557",
  crossref =		 "p10403"
}

@inproceedings{Boularias_IROS_2011,
  author =		 "Boularias, A. and  Kroemer, O. and  Peters, J.",
  year =		 "2011",
  title =		 "Learning Robot Grasping from 3D Images with Markov Random Fields",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robot Systems (IROS)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Boularias_IROS_2011.pdf",
  crossref =		 "p10474"
}

@inproceedings{Kroemer2011NIPS,
  author =		 "Kroemer, O. and  Peters, J.",
  year =		 "2011",
  title =		 "A Non-Parametric Approach to Dynamic Programming",
  booktitle =		 "Advances in Neural Information Processing Systems 25 (NIPS/NeurIPS)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kroemer2011NIPS.pdf",
  publisher =		 "mit press",
  crossref =		 "p10475"
}

@inproceedings{VanHoof_BNAIC_2011,
  author =		 "van Hoof, H. and  van der Zant, T.  and  Wiering, M.A.",
  year =		 "2011",
  title =		 "Adaptive Visual Face Tracking for an Autonomous Robot",
  booktitle =		 "Proceedings of the Belgian-Dutch Artificial Intelligence Conference (BNAIC 11)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/VanHoof_BNAIC_2011.pdf",
  crossref =		 "p10483"
}

@article{Muelling_ABJ2011,
  author =		 "Muelling, K. and  Kober, J. and  Peters, J. ",
  year =		 "2011",
  title =		 "A Biomimetic Approach to Robot Table Tennis",
  booktitle =		 "Adaptive Behavior Journal",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Muelling_ABJ2011.pdf",
  number =		 "5",
  crossref =		 "p10469"
}

@inproceedings{Bocsi_IROS_2011,
  author =		 "Bocsi, B. and  Nguyen-Tuong, D and  Csato, L and  Schoelkopf, B. and  Peters, J.",
  year =		 "2011",
  title =		 "Learning Inverse Kinematics with Structured Prediction",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robot Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Bocsi_IROS_2011.pdf",
  crossref =		 "p10470"
}

@inproceedings{Wang_IROS_2011,
  author =		 "Wang, Z. and  Lampert, C and  Muelling, K and  Schoelkopf, B. and  Peters, J.",
  year =		 "2011",
  title =		 "Learning Anticipation Policies for Robot Table Tennis",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robot Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Wang_IROS_2011.pdf",
  crossref =		 "p10471"
}

@inproceedings{Nguyen_IROS_2011,
  author =		 "Nguyen Tuong, D. and  Peters, J.",
  year =		 "2011",
  title =		 "Learning Task-Space Tracking Control with Kernels",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robot Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Nguyen_IROS_2011.pdf",
  crossref =		 "p10472"
}

@inproceedings{Kober_IROS_2011,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2011",
  title =		 "Learning Elementary Movements Jointly with a Higher Level Task",
  booktitle =		 "IEEE/RSJ International Conference on Intelligent Robot Systems (IROS)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kober_IROS_2011.pdf",
  crossref =		 "p10473"
}

@inproceedings{Gomez_ICORR_2011,
  author =		 "Gomez Rodriguez, M. and  Grosse-Wentrup, M. and  Hill, J. and  Schoelkopf, B. and  Gharabaghi, A. and  Peters, J.",
  year =		 "2011",
  title =		 "Towards Brain-Robot Interfaces for Stroke Rehabilitation",
  booktitle =		 "Proceedings of the International Conference on Rehabilitation Robotics (ICORR)",
  key =			 "team athena-minerva",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Gomez_ICORR_2011.pdf",
  crossref =		 "p10464"
}

@inproceedings{Wang_AAAI_2011,
  author =		 "Wang, Z. and  Boularias, A. and  Muelling, K. and  Peters, J.",
  year =		 "2011",
  title =		 "Balancing Safety and Exploitability in Opponent Modeling",
  booktitle =		 "Proceedings of the Twenty-Fifth National Conference on Artificial Intelligence (AAAI)",
  key =			 "gert",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Wang_AAAI_2011.pdf",
  crossref =		 "p10465"
}

@article{Hachiya_NC2011,
  author =		 "Hachiya, H. and  Peters, J. and  Sugiyama, M.",
  year =		 "2011",
  title =		 "Reward Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning",
  booktitle =		 "Neural Computation",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Hachiya_NC2011.pdf",
  number =		 "11",
  crossref =		 "p10466"
}

@article{Nguyen_CP_2011,
  author =		 "Nguyen Tuong, D. and  Peters, J.",
  year =		 "2011",
  title =		 "Model Learning in Robotics: a Survey",
  booktitle =		 "Cognitive Processing",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Nguyen_CP_2011.pdf",
  number =		 "4",
  crossref =		 "p10461"
}

@inproceedings{Kober_IJCAI_2011,
  author =		 "Kober, J. and  Oztop, E. and  Peters, J.",
  year =		 "2011",
  title =		 "Reinforcement Learning to adjust Robot Movements to New Situations",
  booktitle =		 "Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Best Paper Track",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Kober_IJCAI_2011.pdf",
  crossref =		 "p10462"
}

@inproceedings{boularias11a,
  author =		 "Boularias, A. and  Kober, J. and  Peters, J.",
  year =		 "2011",
  title =		 "Relative Entropy Inverse Reinforcement Learning",
  booktitle =		 "Proceedings of Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2011)",
  key =			 "gert",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/boularias11a.pdf",
  crossref =		 "p10463"
}

@article{jzp049v1_5879,
  author =		 "Wierstra, D. and  Foerster, A. and  Peters, J. and  Schmidhuber, J.",
  year =		 "2010",
  title =		 "Recurrent Policy Gradients",
  booktitle =		 "Logic Journal of the IGPL",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/jzp049v1_5879.pdf",
  pages =		 "620-634",
  crossref =		 "p10217"
}

@inproceedings{RSS2010Kober_64380,
  author =		 "Kober, J. and  Oztop, E. and  Peters, J.",
  year =		 "2010",
  title =		 "Reinforcement Learning to adjust Robot Movements  to New Situations",
  booktitle =		 "Proceedings of Robotics: Science and Systems (R:SS)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/RSS2010-Kober_6438[0].pdf",
  crossref =		 "p10363"
}

@inproceedings{SAB2010Kroemer_64370,
  author =		 "Kroemer, O. and  Detry, R. and  Piater, J. and  Peters, J.",
  year =		 "2010",
  title =		 "Adapting Preshaped Grasping Movements  using Vision Descriptors",
  booktitle =		 " From Animals to Animats 11, International Conference on the  Simulation of Adaptive Behavior (SAB)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/SAB2010-Kroemer_6437[0].pdf",
  crossref =		 "p10364"
}

@inproceedings{ICINCO2010Kroemer_64360,
  author =		 "Kroemer, O. and  Detry, R. and  Piater, J. and  Peters, J.",
  year =		 "2010",
  title =		 "Grasping with Vision Descriptors and  Motor Primitives",
  booktitle =		 "Proceedings of the International Conference on Informatics in Control,  Automation and Robotics (ICINCO)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/ICINCO2010-Kroemer_6436[0].pdf",
  crossref =		 "p10365"
}

@inproceedings{SAB2010Muelling_66260,
  author =		 "Muelling, K. and  Kober, J. and  Peters, J.",
  year =		 "2010",
  title =		 "Simulating Human Table Tennis with a Biomimetic Robot Setup",
  booktitle =		 "From Animals to Animats 11, International Conference on the Simulation of  Adaptive Behavior (SAB)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/SAB2010-Muelling_6626[0].pdf",
  crossref =		 "p10366"
}

@inproceedings{AISTATS2010NguyenTuong,
  author =		 "Nguyen Tuong, D. and  Peters, J.",
  year =		 "2010",
  title =		 "Incremental Sparsification for Real-time Online Model Learning",
  booktitle =		 "Proceedings of Thirteenth International Conference on  Artificial Intelligence and Statistics (AISTATS 2010)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/AISTATS2010-Nguyen-Tuong.pdf",
  crossref =		 "p10350"
}

@article{kober_RAM_2010,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2010",
  title =		 "Imitation and Reinforcement Learning - Practical Algorithms for Motor Primitive Learning in Robotics",
  booktitle =		 "IEEE Robotics and Automation Magazine",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/kober_RAM_2010.pdf",
  number =		 "2",
  pages =		 "55-62",
  crossref =		 "p10351"
}

@article{KroemerJRAS_66360,
  author =		 "Kroemer, O. and  Detry, R. and  Piater, J. and  Peters, J.",
  year =		 "2010",
  title =		 "Combining Active Learning and Reactive Control for Robot Grasping",
  booktitle =		 "Robotics and Autonomous Systems",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/KroemerJRAS_6636[0].pdf",
  number =		 "9",
  pages =		 "1105-1116",
  crossref =		 "p10357"
}

@inbook{LGP_IROS_Chapter_6233,
  author =		 "Nguyen Tuong, D. and  Peters, J. and Seeger, M.",
  year =		 "2010",
  title =		 "Real-Time Local GP Model Learning",
  booktitle =		 "From Motor Learning to Interaction Learning in Robots, Springer Verlag",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/LGP_IROS_Chapter_6233.pdf",
  number =		 "264",
  crossref =		 "p10317"
}

@inbook{EncyclopediaMachineLearningPetersRobotLearning_0,
  author =		 "Peters, J. and  Tedrake, R. and  Roy, N. and  Morimoto, J.",
  year =		 "2010",
  title =		 "Robot Learning",
  booktitle =		 "Encyclopedia of Machine Learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/EncyclopediaMachineLearning-Peters-RobotLearning_[0].pdf",
  crossref =		 "p10318"
}

@book{9783642051814,
  author =		 "Sigaud, O. and  Peters, J.",
  year =		 "2010",
  title =		 "From Motor Learning to Interaction Learning in Robots",
  booktitle =		 "Studies in Computational Intelligence, Springer Verlag",
  URL =			 "http://dx.doi.org/10.1007/978-3-642-05181-4",
  number =		 "264",
  crossref =		 "p10319"
}

@inbook{Imitation20and20Reinforcement20Learning20for20Motor20Primitives20with20Perceptual20Coupling_62340,
  author =		 "Kober, J. and  Mohler, B. and  Peters, J.",
  year =		 "2010",
  title =		 "Imitation and Reinforcement Learning for Motor Primitives with Perceptual Coupling",
  booktitle =		 "From Motor Learning to Interaction Learning in Robots, Springer Verlag",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Imitation%20and%20Reinforcement%20Learning%20for%20Motor%20Primitives%20with%20Perceptual%20Coupling_6234[0].pdf",
  crossref =		 "p10320"
}

@inproceedings{Peters2010_REPS,
  author =		 "Peters, J. and  Muelling, K. and  Altun, Y.",
  year =		 "2010",
  title =		 "Relative Entropy Policy Search",
  booktitle =		 "Proceedings of the Twenty-Fourth National Conference on Artificial Intelligence (AAAI), Physically Grounded AI Track",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Team/JanPeters/Peters2010_REPS.pdf",
  crossref =		 "p10362"
}

@inproceedings{ICRA2010Kober_62311,
  author =		 "Kober, J. and  Muelling, K. and  Kroemer, O. and  Lampert, C.H. and  Schoelkopf, B. and  Peters, J.",
  year =		 "2010",
  title =		 "Movement Templates for Learning of Hitting and Batting",
  booktitle =		 "IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/ICRA2010-Kober_6231[1].pdf",
  crossref =		 "p10314"
}

@inproceedings{ICRA2010NguyenTuong_6232,
  author =		 "Nguyen Tuong, D. and  Peters, J.",
  year =		 "2010",
  title =		 "Using Model Knowledge for Learning Inverse Dynamics",
  booktitle =		 "IEEE International Conference on Robotics and Automation",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICRA2010-NguyenTuong_6232.pdf",
  crossref =		 "p10315"
}

@article{NeuralNetworks2010Sehnke,
  author =		 "Sehnke, F. and  Osendorfer, C. and  Rueckstiess, T. and  Graves, A. and  Peters, J. and  Schmidhuber, J.",
  year =		 "2010",
  title =		 "Parameter-exploring Policy Gradients",
  booktitle =		 "Neural Networks",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Neural-Networks-2010-Sehnke.pdf",
  crossref =		 "p10311"
}

@inbook{Peters_EOMLA_submitted_60740,
  author =		 "Peters, J. and  Bagnell, J.A.",
  year =		 "2010",
  title =		 "Policy gradient methods",
  booktitle =		 "Encyclopedia of Machine Learning (invited article)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Peters_EOMLA_submitted_6074[0].pdf",
  crossref =		 "p10302"
}

@article{LSD_revise_ver3_59040,
  author =		 "Morimura, T. and  Uchibe, E. and  Yoshimoto, J. and  Peters, J. and  Doya, K.",
  year =		 "2010",
  title =		 "Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning",
  booktitle =		 "Neural Computation",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/LSD_revise_ver3_5904[0].pdf",
  number =		 "2",
  crossref =		 "p10297"
}

@inbook{Detry2010MotorInteractionLearning_0,
  author =		 "Detry, R. and  Baseski, E. and  Popovic, M. and  Touati, Y. and  Krueger, N. and  Kroemer, O. and   Peters, J. and  Piater, J.",
  year =		 "2010",
  title =		 "Learning Continuous Grasp Affordances by Sensorimotor Exploration",
  booktitle =		 "From Motor Learning to Interaction Learning in Robots, Springer Verlag",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Detry-2010-MotorInteractionLearning_[0].pdf",
  number =		 "264",
  crossref =		 "p10326"
}

@inproceedings{erkan_IROS_2010,
  author =		 "Erkan, A.: Kroemer, O. and  Detry, R. and  Altun, Y. and  Piater, J. and  Peters, J.",
  year =		 "2010",
  title =		 "Learning Probabilistic Discriminative Models of Grasp Affordances under Limited Supervision",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  key =			 "gert",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/erkan_IROS_2010.pdf",
  crossref =		 "p10370"
}

@inproceedings{Muelling_ABJ2011,
  author =		 "Muelling, K. and  Kober, J. and  Peters, J.",
  year =		 "2010",
  title =		 "A Biomimetic Approach to Robot Table Tennis",
  booktitle =		 "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/Muelling_ABJ2011.pdf",
  crossref =		 "p10371"
}

@inproceedings{ICPRWBD2010GomezRodriguez,
  author =		 "Gomez Rodriguez, M. and  Grosse Wentrup, M. and  Peters, J. and  Naros, G. and  Hill, J. and  Gharabaghi, A. and  Schoelkopf, B.",
  year =		 "2010",
  title =		 "Epidural ECoG Online Decoding of Arm Movement Intention in Hemiparesis",
  booktitle =		 "1st ICPR Workshop on Brain Decoding: Pattern Recognition Challenges in Neuroimaging",
  key =			 "team athena-minerva",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICPR-WBD-2010-Gomez-Rodriguez.pdf",
  crossref =		 "p10372"
}

@inproceedings{eegsmc2010_6591,
  author =		 "Gomez Rodriguez, M. and  Peters, J. and  Hill, J. and  Schoelkopf, B. and  Gharabaghi, A. and  Grosse-Wentrup, M.",
  year =		 "2010",
  title =		 "Closing the Sensorimotor Loop: Haptic Feedback Facilitates Decoding of Arm Movement Imagery",
  booktitle =		 "Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics  (Workshop on Brain-Machine Interfaces)",
  key =			 "team athena-minerva",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/eeg-smc2010_6591.pdf",
  crossref =		 "p10373"
}

@inproceedings{,
  author =		 "Gomez Rodriguez, M. and  Peters, J. and  Hill, J. and  Gharabaghi, A. and  Schoelkopf, B. and  Grosse-Wentrup, M.",
  year =		 "2010",
  title =		 "BCI and robotics framework for stroke rehabilitation",
  booktitle =		 "Proceedings of the 4th International BCI Meeting, May 31 - June 4, 2010. Asilomar, CA, USA",
  key =			 "team athena-minerva",
  URL =			 "http://bcimeeting.org/2010/",
  crossref =		 "p10374"
}

@inproceedings{lamperteccv2010,
  author =		 "Lampert, C. H. and  Kroemer, O.",
  year =		 "2010",
  title =		 "Weakly-Paired Maximum Covariance Analysis for Multimodal Dimensionality Reduction and Transfer Learning",
  booktitle =		 "Proceedings of the 11th European Conference on Computer Vision (ECCV 2010)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/lampert-eccv2010.pdf",
  crossref =		 "p10389"
}

@inproceedings{Chiappa_NIPS_2011,
  author =		 "Chiappa, S. and  Peters, J.",
  year =		 "2010",
  title =		 "Movement extraction by detecting dynamics switches and	repetitions",
  booktitle =		 "Advances in Neural Information Processing Systems 24 (NIPS/NeurIPS), Cambridge, MA: MIT Press",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Chiappa_NIPS_2011.pdf",
  crossref =		 "p10390"
}

@inproceedings{Alvarez_NIPS_2011,
  author =		 "Alvaro, M. and  Peters, J. and  Schoelfkopf, B. and  Lawrence, N.",
  year =		 "2010",
  title =		 "Switched Latent Force Models for Movement Segmentation",
  booktitle =		 "Advances in Neural Information Processing Systems 24 (NIPS/NeurIPS), Cambridge, MA: MIT Press",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Alvarez_NIPS_2011.pdf",
  crossref =		 "p10391"
}

@article{Peters_A_2010,
  author =		 "Peters, J. and Kober, J. and Schaal, S.",
  year =		 "2010",
  title =		 "Policy learning algorithmis for motor learning (Algorithmen zum automatischen Erlernen von Motorfaehigkigkeiten)",
  booktitle =		 "Automatisierungstechnik",
  key =			 "reinforcement leanring, motor skills",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/at-Automatisierungstechnik-Algorithmen_zum_Automatischen_Erlernen_von_Motorfhigkeiten",
  number =		 "12",
  pages =		 "688-694",
  crossref =		 "p10417"
}

@inproceedings{Muelling_ICHR_2012,
  author =		 "Muelling, K. and  Kober, J. and  Peters, J.",
  year =		 "2010",
  title =		 "Learning Table Tennis with a Mixture of Motor Primitives",
  booktitle =		 "10th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2010)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Muelling_ICHR_2012.pdf",
  crossref =		 "p10560"
}

@inproceedings{Peters_ISER_2010,
  author =		 "Peters, J. and  Muelling, K. and  Kober, J.",
  year =		 "2010",
  title =		 "Experiments with Motor Primitives to learn Table Tennis",
  booktitle =		 "12th International Symposium on Experimental Robotics (ISER 2010)",
  crossref =		 "p10562"
}

@inproceedings{ECMLPKDD2009Hachiya_60680,
  author =		 "Hachiya, H. and  Peters, J. and  Sugiyama, M.",
  year =		 "2009",
  title =		 "Efficient Sample Reuse in EM-based Policy Search",
  booktitle =		 "Proceedings of the 16th European Conference on Machine Learning (ECML 2009)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ECML-PKDD-2009-Hachiya_6068[0].pdf",
  crossref =		 "p10298"
}

@inproceedings{peters_ISRR_2007,
  author =		 "Peters, J. and  Kober, J. and  Muelling, K. and  Nguyen-Tuong, D. and  Kroemer, O.",
  year =		 "2009",
  title =		 "Towards Motor Skill Learning for Robotics",
  booktitle =		 "Proceedings of the International Symposium on Robotics Research (ISRR), Invited Paper",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/peters_ISRR_2007.pdf",
  crossref =		 "p10300"
}

@inproceedings{3403localgaussianprocessregressionforrealtimeonlinemodellearning,
  author =		 "Nguyen Tuong, D. and  Seeger, M. and  Peters, J.",
  year =		 "2009",
  title =		 "Local Gaussian Process Regression for Real Time Online Model Learning and Control",
  booktitle =		 "Advances in Neural Information Processing Systems 22 (NIPS/NeurIPS), Cambridge, MA: MIT Press",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/3403-local-gaussian-process-regression-for-real-time-online-model-learning.pdf",
  crossref =		 "p10194"
}

@inproceedings{NIPS2008Neumann_55205B05D,
  author =		 "Neumann, G. and  Peters, J.",
  year =		 "2009",
  title =		 "Fitted Q-iteration by Advantage Weighted Regression",
  booktitle =		 "Advances in Neural Information Processing Systems 22 (NIPS/NeurIPS), Cambridge, MA: MIT Press",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NIPS2008-Neumann_5520%5B0%5D.pdf",
  crossref =		 "p10196"
}

@article{hachiyaAdaptiveImportanceSampling_5530,
  author =		 "Hachiya, H. and  Akiyama, T. and  Sugiyama, M. and  Peters, J.",
  year =		 "2009",
  title =		 "Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning",
  booktitle =		 "Neural Networks",
  key =			 "off-policy reinforcement learning and  value function approximation and  policy iteration and  adaptive importance sampling and  importance-weighted cross-validation and  efficient sample reuse",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/hachiya-AdaptiveImportanceSampling_5530.pdf",
  number =		 "10",
  pages =		 "1399-1410",
  crossref =		 "p10198"
}

@inproceedings{NIPS2008KoberPeters_54110,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2009",
  title =		 "Policy Search for Motor Primitives in Robotics",
  booktitle =		 "Advances in Neural Information Processing Systems 22 (NIPS/NeurIPS), Cambridge, MA: MIT Press",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NIPS2008-Kober-Peters_5411[0].pdf",
  crossref =		 "p10192"
}

@inproceedings{NIPS2008Chiappa_54000,
  author =		 "Chiappa, S. and  Kober, J. and  Peters, J.",
  year =		 "2009",
  title =		 "Using Bayesian Dynamical Systems for Motion Template Libraries",
  booktitle =		 "Advances in Neural Information Processing Systems 22 (NIPS/NeurIPS), Cambridge, MA: MIT Press",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NIPS2008-Chiappa_5400[0].pdf",
  crossref =		 "p10193"
}

@article{Neurocomputing2009DeisenrothPreprint_5531,
  author =		 "Deisenroth, M.P. and  Rasmussen, C.E. and  Peters, J.",
  year =		 "2009",
  title =		 "Gaussian Process Dynamic Programming",
  booktitle =		 "Neurocomputing",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Neurocomputing-2009-Deisenroth-Preprint_5531.pdf",
  number =		 "72",
  pages =		 "1508-1524",
  crossref =		 "p10200"
}

@inproceedings{AIStats2009Hoffman_5658,
  author =		 "Hoffman, M. and  de Freitas, N.  and  Doucet, A. and  Peters, J.",
  year =		 "2009",
  title =		 "An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward",
  booktitle =		 "Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AIStats)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/AIStats2009-Hoffman_5658.pdf",
  crossref =		 "p10204"
}

@inproceedings{peters_ADPRL_2009,
  author =		 "Peters, J. and  Kober, J.",
  year =		 "2009",
  title =		 "Using Reward-Weighted Imitation for Robot Reinforcement Learning",
  booktitle =		 "Proceedings of the 2009 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/peters_ADPRL_2009.pdf",
  crossref =		 "p10205"
}

@inproceedings{ADPRL2009Hachiya,
  author =		 "Hachiya, H. and  Akiyama, T. and  Sugiyama, M. and  Peters, J.",
  year =		 "2009",
  title =		 "Efficient Data Reuse in Value Function Approximation",
  booktitle =		 "Proceedings of the 2009 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ADPRL2009-Hachiya.pdf",
  crossref =		 "p10206"
}

@inproceedings{ICRA2009Kober_56610,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2009",
  title =		 "Learning Motor Primitives for Robotics",
  booktitle =		 "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/ICRA2009-Kober_5661[0].pdf",
  crossref =		 "p10207"
}

@inproceedings{Piater2009ISRR,
  author =		 "Piater, J. and  Jodogne, S. and  Detry, R. and  Kraft, D. and  Krueger, N. and   Kroemer, O. and  Peters, J.",
  year =		 "2009",
  title =		 "Learning Visual Representations for Interactive Systems",
  booktitle =		 "Proceedings of the International Symposium on Robotics Research (ISRR), Invited Paper",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Piater-2009-ISRR.pdf",
  crossref =		 "p10299"
}

@inproceedings{paper_16,
  author =		 "Kober, J. and  Peters,  J. ",
  year =		 "2009",
  title =		 "Learning new basic Movements for Robotics",
  booktitle =		 "Proceedings of Autonome Mobile Systeme (AMS 2009)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/paper_16.pdf",
  crossref =		 "p10322"
}

@inproceedings{A_computational_model_of_human_table_tennis,
  author =		 "Muelling, K. and  Peters, J.",
  year =		 "2009",
  title =		 "A computational model of human table tennis for robot application",
  booktitle =		 "Proceedings of Autonome Mobile Systeme (AMS 2009)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/A_computational_model_of_human_table_tennis.pdf",
  crossref =		 "p10323"
}

@inproceedings{kroemer_IROS_2009,
  author =		 "Kroemer, O. and  Detry, R. and  Piater, J. and  Peters, J.",
  year =		 "2009",
  title =		 "Active Learning Using Mean Shift Optimization for Robot Grasping",
  booktitle =		 "Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/kroemer_IROS_2009.pdf",
  crossref =		 "p10324"
}

@inproceedings{Sparse_Online_Model_Learning_for_Robot_Control,
  author =		 "Nguyen Tuong, D. and  Seeger, M. and  Peters, J.",
  year =		 "2009",
  title =		 "Sparse Online Model Learning for Robot Control with Support Vector Regression",
  booktitle =		 "Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Sparse_Online_Model_Learning_for_Robot_Control.pdf",
  crossref =		 "p10325"
}

@article{PetersNg2009_Article_GuestEditorialSpecialIssueOnRo,
  author =		 "Peters, J. and  Ng, A.",
  year =		 "2009",
  title =		 "Guest Editorial: Special Issue on Robot Learning, Part B",
  booktitle =		 "Autonomous Robots (AURO)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Peters-Ng2009_Article_GuestEditorialSpecialIssueOnRo.pdf",
  number =		 "2",
  crossref =		 "p10312"
}

@inproceedings{JNRR2009Sigaud_0,
  author =		 "Sigaud, O. and  Peters, J.",
  year =		 "2009",
  title =		 "From Motor Learning to Interaction Learning in Robots",
  booktitle =		 "Proceedings of Journees Nationales de la Recherche en Robotique",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/JNRR2009-Sigaud_[0].pdf",
  crossref =		 "p10313"
}

@inproceedings{ICML2009Neumann,
  author =		 "Neumann, G. and  Maass, W and  Peters, J.",
  year =		 "2009",
  title =		 "Learning Complex Motions by Sequencing Simpler Motion Templates",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML2009)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICML2009-Neumann.pdf",
  crossref =		 "p10290"
}

@inproceedings{ICDL2009Detry_0,
  author =		 "Detry, R and  Baseski, E. and  Popovic, M. and  Touati, Y. and  Krueger, N and  Kroemer, O. and  Peters, J. and  Piater, J and ",
  year =		 "2009",
  title =		 "Learning Object-specific Grasp Affordance Densities",
  booktitle =		 "Proceedings of the International Conference on Development &  Learning (ICDL 2009)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/ICDL2009-Detry_[0].pdf",
  crossref =		 "p10291"
}

@article{NguyenTuongModelLearningLocalGaussian,
  author =		 "Nguyen Tuong, D. and  Seeger, M. and  Peters, J.",
  year =		 "2009",
  title =		 "Model Learning with Local Gaussian Process Regression",
  booktitle =		 "Advanced Robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Nguyen-Tuong-ModelLearningLocalGaussian.pdf",
  number =		 "15",
  pages =		 "2015-2034",
  crossref =		 "p10301"
}

@article{index,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2009",
  title =		 "Reinforcement Learning fuer Motor-Primitive",
  booktitle =		 "Kuenstliche Intelligenz",
  URL =			 "http://www.kuenstliche-intelligenz.de/index.php?id=7779&tx_ki_pi1[showUid]=1820&cHash=a9015a9e57",
  crossref =		 "p10292"
}

@article{05233410,
  author =		 "Peters, J. and  Morimoto, J. and  Tedrake, R. and  Roy, N.",
  year =		 "2009",
  title =		 "Robot Learning",
  booktitle =		 "IEEE Robotics & Automation Magazine",
  key =			 "robot learning, tc spotlight",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/05233410.pdf",
  number =		 "3",
  pages =		 "19-20",
  crossref =		 "p10294"
}

@article{PetersNg2009_Article_GuestEditorialSpecialIssueOnRo,
  author =		 "Peters, J. and  Ng, A.",
  year =		 "2009",
  title =		 "Guest Editorial: Special Issue on Robot Learning, Part A",
  booktitle =		 "Autonomous Robots (AURO)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Peters-Ng2009_Article_GuestEditorialSpecialIssueOnRo.pdf",
  number =		 "1",
  crossref =		 "p10295"
}

@inproceedings{DAGM2009Lampert,
  author =		 "Lampert, C.H. and  Peters, J.",
  year =		 "2009",
  title =		 "Active Structured Learning for High-Speed Object Detection",
  booktitle =		 "Proceedings of the DAGM (Pattern Recognition)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/DAGM2009-Lampert.pdf",
  crossref =		 "p10296"
}

@inproceedings{ICCP09GomezRodriguez_54910,
  author =		 "Gomez Rodriguez, M. and  Kober, J. and  Schoelkopf, B.",
  year =		 "2009",
  title =		 "Denoising photographs using dark frames optimized by quadratic programming",
  booktitle =		 "Proceedings of the First IEEE International Conference on Computational Photography (ICCP 2009)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/ICCP09-GomezRodriguez_5491[0].pdf",
  crossref =		 "p10400"
}

@inproceedings{deisenroth_ACC2008,
  author =		 "Deisenroth, M.P. and  Peters, J. and  Rasmussen, C.E.",
  year =		 "2008",
  title =		 "Approximate Dynamic Programming with Gaussian Processes",
  booktitle =		 "American Control Conference",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Main/PublicationsByYear/deisenroth_ACC2008.pdf",
  crossref =		 "p10148"
}

@inproceedings{NguyenTuong_ACC2008,
  author =		 "Peters, J. and  Seeger, M.",
  year =		 "2008",
  title =		 "Computed Torque Control with Nonparametric Regressions Techniques",
  booktitle =		 "American Control Conference",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NguyenTuong_ACC2008.pdf",
  crossref =		 "p10149"
}

@inproceedings{deisenroth_ESANN2008,
  author =		 "Deisenroth, M.P. and  Rasmussen, C.E. and  Peters, J.",
  year =		 "2008",
  title =		 "Model-Based Reinforcement Learning with Continuous States and Actions",
  booktitle =		 "Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/deisenroth_ESANN2008.pdf",
  pages =		 "19-24",
  crossref =		 "p10155"
}

@article{Steinke_EGFinal1049,
  author =		 "Steinke, F. and  Hein, M. and  Peters, J. and  Schoelkopf, B",
  year =		 "2008",
  title =		 "Manifold-valued Thin-Plate Splines with Applications in Computer Graphics",
  booktitle =		 "Computer Graphics Forum (Special Issue on Eurographics 2008)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Steinke_EGFinal-1049.pdf",
  number =		 "2",
  crossref =		 "p10154"
}

@inproceedings{NguyenTuong_ACC2008,
  author =		 "Nguyen Tuong, D. and  Peters, J.",
  year =		 "2008",
  title =		 "Learning Inverse Dynamics: a Comparison",
  booktitle =		 "Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008)",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NguyenTuong_ACC2008.pdf",
  crossref =		 "p10156"
}

@inproceedings{ICRA2008Peters_48650,
  author =		 "Peters, J. and  Nguyen-Tuong, D.",
  year =		 "2008",
  title =		 "Real-Time Learning of Resolved Velocity Control on a Mitsubishi PA-10",
  booktitle =		 "International Conference on Robotics and Automation (ICRA)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICRA2008-Peters_4865[0].pdf",
  crossref =		 "p10151"
}

@inproceedings{AAAI2008Hachiya_50960,
  author =		 "Hachiya, H. and  Akiyama, T. and  Sugiyama, M. and  Peters, J.",
  year =		 "2008",
  title =		 "Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation",
  booktitle =		 "Proceedings of the Twenty-Third National Conference on Artificial Intelligence (AAAI 2008)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/AAAI-2008-Hachiya_5096[0].pdf",
  crossref =		 "p10163"
}

@inproceedings{wierstraCEC2008,
  author =		 "Wierstra, D. and  Schaul, T. and  Peters, J. and  Schmidhuber, J.",
  year =		 "2008",
  title =		 "Natural Evolution Strategies",
  booktitle =		 "2008 IEEE Congress on Evolutionary Computation",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/wierstra-CEC2008.pdf",
  crossref =		 "p10164"
}

@inproceedings{IROS2008Nguyen_0,
  author =		 "Nguyen Tuong, D. and  Peters, J.",
  year =		 "2008",
  title =		 "Local Gaussian Processes Regression for Real-time Model-based Robot Control",
  booktitle =		 "International Conference on Intelligent Robot Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IROS2008-Nguyen_[0].pdf",
  crossref =		 "p10170"
}

@inproceedings{IROS2008Kober_54140,
  author =		 "Kober, J. and  Mohler, B. and  Peters, J.",
  year =		 "2008",
  title =		 "Learning Perceptual Coupling for Motor Primitives",
  booktitle =		 "International Conference on Intelligent Robot Systems (IROS)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IROS2008-Kober_5414[0].pdf",
  crossref =		 "p10171"
}

@book{Lesperance_JPGI_2008,
  author =		 "Lesperance, Y. and  Lakemeyer, G. and  Peters, J. and  Pirri, F.",
  year =		 "2008",
  title =		 "Proceedings of the 6th International Cognitive Robotics Workshop (CogRob 2008)",
  booktitle =		 "July 21-22, 2008, Patras, Greece, ISBN 978-960-6843-09-9",
  crossref =		 "p10195"
}

@inproceedings{ppsn08,
  author =		 "Wierstra, D. and   Schaul, T. and  Peters, J. and  Schmidthuber, J.",
  year =		 "2008",
  title =		 "Fitness Expectation Maximization",
  booktitle =		 "10th International Conference on Parallel Problem Solving from Nature (PPSN 2008)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ppsn08.pdf",
  crossref =		 "p10189"
}

@article{Nakanishi_IJRR_2008,
  author =		 "Nakanishi, J. and Cory, R. and Mistry, M. and Peters, J. and Schaal, S.",
  year =		 "2008",
  title =		 "Operational space control: A theoretical and empirical comparison",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  key =			 "task space control, operational space control, redundancy resolution, humanoid robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Int-J-Robot-Res-2008-27-737_5027[0].pdf",
  number =		 "6",
  pages =		 "737-757",
  crossref =		 "p3236"
}

@inproceedings{wierstra_ICANN08,
  author =		 "Wierstra, D. and  Schaul,T. and  Peters, J. and  Schmidhuber, J.",
  year =		 "2008",
  title =		 "Episodic Reinforcement Learning by Logistic Reward-Weighted Regression",
  booktitle =		 "Proceedings of the International Conference on Artificial Neural Networks (ICANN)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/wierstra_ICANN08.pdf",
  crossref =		 "p10183"
}

@inproceedings{icann2008sehnke,
  author =		 "Sehnke, F. and  Osendorfer, C and  Rueckstiess, T and  Graves, A. and  Peters, J. and  Schmidhuber, J.",
  year =		 "2008",
  title =		 "Policy Gradients with Parameter-based Exploration for Control",
  booktitle =		 "Proceedings of the International Conference on Artificial Neural Networks (ICANN)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/icann2008sehnke.pdf",
  crossref =		 "p10184"
}

@book{refsr_1_1ieUTF8sbooksqid1220658804sr81,
  author =		 "Peters, J.",
  year =		 "2008",
  title =		 "Machine Learning for Robotics",
  booktitle =		 "VDM-Verlag, ISBN 978-3-639-02110-3",
  URL =			 "http://www.amazon.de/Machine-Learning-Robotics-Methods-Skills/dp/363902110X/ref=sr_1_1?ie=UTF8&s=books&qid=1220658804&sr=8-1",
  ISBN/ISSN =		 "ISBN 978-3-639-02110-3",
  crossref =		 "p10185"
}

@inproceedings{8808e934beb11e344433a6c98a68269e26f1,
  author =		 "Peters, J. and  Kober, J. and  Nguyen-Tuong, D.",
  year =		 "2008",
  title =		 "Policy Learning - a unified perspective with applications in robotics",
  booktitle =		 "Proceedings of the European Workshop on Reinforcement Learning (EWRL)",
  key =			 "reinforcement learning, policy gradient, weighted regression",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/8808e934beb11e344433a6c98a68269e26f1.pdf",
  crossref =		 "p10186"
}

@inproceedings{Kober_PEWRL_2008,
  author =		 "Kober, J. and  Peters, J.",
  year =		 "2008",
  title =		 "Reinforcement Learning of Perceptual Coupling for Motor Primitives",
  booktitle =		 "Proceedings of the European Workshop on Reinforcement Learning (EWRL)",
  crossref =		 "p10187"
}

@article{KuenstlicheIntelligenz2008Peters_0,
  author =		 "Peters, J.",
  year =		 "2008",
  title =		 "Machine Learning for Motor Skills in Robotics",
  booktitle =		 "Kuenstliche Intelligenz",
  key =			 "motor control, motor primitives, motor learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/KuenstlicheIntelligenz-2008-Peters_[0].pdf",
  number =		 "3",
  crossref =		 "p10188"
}

@inproceedings{nguyenecsis,
  author =		 "Nguyen Tuong, D. and  Peters, J. and  Seeger, M. and  Schoelkopf, B.",
  year =		 "2008",
  title =		 "Learning Robot Dynamics for Computed Torque Control using Local Gaussian Processes Regression",
  booktitle =		 "Proceedings of the ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, LAB-RS 2008",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/nguyen-ecsis.pdf",
  crossref =		 "p10191"
}

@article{Peters_N_2008,
  author =		 "Peters, J. and  Schaal, S.",
  year =		 "2008",
  title =		 "Natural actor critic",
  booktitle =		 "Neurocomputing",
  key =			 "reinforcement learning, policy gradient, natural actor-critic, natural gradients",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NEUCOM-D-07-00618-1_[0].pdf",
  number =		 "7-9",
  pages =		 "1180-1190",
  crossref =		 "p10233"
}

@article{Learning_to_Control_in_Operational_Space,
  author =		 "Peters, J. and  Schaal, S.",
  year =		 "2008",
  title =		 "Learning to control in operational space",
  booktitle =		 "International Journal of Robotics Research (IJRR)",
  key =			 "operational space control, learning, em algorithm, redundancy resolution, reinforcement learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JanPeters/Learning_to_Control_in_Operational_Space.pdf",
  pages =		 "197-212",
  crossref =		 "p10235"
}

@article{Peters_NN_2008,
  author =		 "Peters, J. and  Schaal, S.",
  year =		 "2008",
  title =		 "Reinforcement learning of motor skills with policy gradients",
  booktitle =		 "Neural Networks",
  key =			 "reinforcement learning, policy gradient methods, natural gradients, natural actor-critic, motor skills, motor primitives",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Neural-Netw-2008-21-682_4867[0].pdf",
  number =		 "4",
  pages =		 "682-97",
  ISBN/ISSN =		 "0893-6080 (Print)",
  crossref =		 "p10271"
}

@article{Peters_AR_2008,
  author =		 "Peters, J. and Mistry, M. and Udwadia, F. E. and Nakanishi, J. and Schaal, S.",
  year =		 "2008",
  title =		 "A unifying framework for robot control with redundant DOFs",
  booktitle =		 "Autonomous Robots (AURO)",
  key =			 "operational space control, inverse control, dexterous manipulation, optimal control",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/AR-2008final_[0].pdf",
  number =		 "1",
  pages =		 "1-12",
  crossref =		 "p10273"
}

@phdthesis{DiplomaThesisKober_53310,
  author =		 "Kober, J.",
  year =		 "2008",
  title =		 "Reinforcement Learning for Motor Primitives",
  booktitle =		 "Dipl-Ing Thesis, University of Stuttgart",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/publications/DiplomaThesis-Kober_5331[0].pdf",
  crossref =		 "p10401"
}

@article{Peters_TCJ_2007,
  author =		 "Peters, J.",
  year =		 "2007",
  title =		 "Computational Intelligence: By Amit Konar",
  booktitle =		 "The Computer Journal",
  key =			 "book review",
  number =		 "6",
  pages =		 "758",
  crossref =		 "p10137"
}

@inproceedings{ICONIP2007Peters_48690,
  author =		 "Peters, J. and  Schaal, S.",
  year =		 "2007",
  title =		 "Policy Learning for Motor Skills",
  booktitle =		 "Proceedings of 14th International Conference on Neural Information Processing (ICONIP)",
  key =			 "machine learning, reinforcement learning, robotics, motor primitives, policy gradients, natural actor-critic, reward-weighted regression",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICONIP2007-Peters_4869[0].pdf",
  crossref =		 "p10136"
}

@inproceedings{icann2007,
  author =		 "Wierstra, D. and  Foerster, A. and  Peters, J. and  Schmidhuber, J.",
  year =		 "2007",
  title =		 "Solving Deep Memory POMDPs with Recurrent Policy Gradients",
  booktitle =		 "Proceedings of the International Conference on Artificial Neural Networks (ICANN)",
  key =			 "policy gradients, reinforcement learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/icann2007.pdf",
  crossref =		 "p10132"
}

@inproceedings{Peters_POAMS_2007,
  author =		 "Peters, J. and  Schaal, S. and  Schoelkopf, B.",
  year =		 "2007",
  title =		 "Towards Machine Learning of Motor Skills",
  booktitle =		 "Proceedings of Autonome Mobile Systeme (AMS)",
  key =			 "motor skill learning, robotics, natural actor-critic, reward-weighted regeression",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Peters_POAMS_2007.pdf",
  crossref =		 "p10121"
}

@inproceedings{Theodorou_AMSN_2007,
  author =		 "Theodorou, E and  Peters, J. and  Schaal, S.",
  year =		 "2007",
  title =		 "Reinforcement Learning for Optimal Control of Arm Movements",
  booktitle =		 "Abstracts of the 37st Meeting of the Society of Neuroscience",
  key =			 "optimal control,reinforcement learning, arm movements",
  crossref =		 "p10123"
}

@article{Nakanishi_IICIRS_2007,
  author =		 "Nakanishi, J. and  Mistry, M. and  Peters, J. and  Schaal, S.",
  year =		 "2007",
  title =		 "Experimental evaluation of task space position/orientation control towards compliant control for humanoid robots",
  booktitle =		 "IEEE International Conference on Intelligent Robotics Systems (IROS 2007)",
  key =			 "operational space control, quaternion, task space control, resolved motion rate control, resolved acceleration, force control",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IROS2007-Nakanishi_4722[0].pdf",
  crossref =		 "p3019"
}

@phdthesis{Peters_PTDCSUSC_2007,
  author =		 "Peters, J.",
  year =		 "2007",
  title =		 "Machine Learning of Motor Skills for Robotics",
  booktitle =		 "Ph.D. Thesis, Department of Computer Science, University of Southern California",
  key =			 "machine learning, reinforcement learning, robotics, motor primitives, policy gradients, natural actor-critic, reward-weighted regression",
  crossref =		 "p10135"
}

@inproceedings{ICRA20072111_0,
  author =		 "Peters, J. and  Schaal, S.",
  year =		 "2007",
  title =		 "Reinforcement learning for operational space control",
  booktitle =		 "International Conference on Robotics and Automation (ICRA2007)",
  key =			 "operational space control, reinforcement learning, weighted regression, em-algorithm",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICRA2007-2111_[0].pdf",
  crossref =		 "p2670"
}

@inproceedings{Peters_PIISADPRL_2007,
  author =		 "Peters, J. and Schaal, S.",
  year =		 "2007",
  title =		 "Using reward-weighted regression for reinforcement learning of task space control",
  booktitle =		 "Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning",
  key =			 "reinforcement learning, cart-pole, policy gradient methods",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ADPRL2007-Peters_[0].pdf",
  crossref =		 "p2672"
}

@inproceedings{Peters_PESANN_2007,
  author =		 "Peters, J. and  Schaal, S.",
  year =		 "2007",
  title =		 "Applying the episodic natural actor-critic architecture to motor primitive learning",
  booktitle =		 "Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN)",
  key =			 "reinforcement learning, policy gradient methods, motor primitives, natural actor-critic",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/es2007-125.pdf",
  crossref =		 "p2673"
}

@inproceedings{Peters_PICML_2007,
  author =		 "Peters, J. and Schaal, S.",
  year =		 "2007",
  title =		 "Reinforcement learning by reward-weighted regression for operational space control",
  booktitle =		 "Proceedings of the International Conference on Machine Learning (ICML2007)",
  key =			 "reinforcement learning, operational space control, weighted regression",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ICML2007-Peters_4493[0].pdf",
  crossref =		 "p2675"
}

@inproceedings{Peters_ICAPS_2007,
  author =		 "Peters, J. and Theodorou, E. and Schaal, S.",
  year =		 "2007",
  title =		 "Policy gradient methods for machine learning",
  booktitle =		 "INFORMS Conference of the Applied Probability Society",
  key =			 "policy gradient methods, reinforcement learning, simulation-optimization",
  crossref =		 "p2674"
}

@inproceedings{Riedmiller_PIISADPRL_2007,
  author =		 "Riedmiller, M. and Peters, J. and Schaal, S.",
  year =		 "2007",
  title =		 "Evaluation of policy gradient methods and variants on the cart-pole benchmark",
  booktitle =		 "Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning",
  key =			 "reinforcement learning, cart-pole, policy gradient methods",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ADPRL2007-Peters2_[0].pdf",
  crossref =		 "p2654"
}

@techreport{PetersTR2007,
  author =		 "Peters, J.",
  year =		 "2007",
  title =		 "Relative Entropy Policy Search",
  booktitle =		 "CLMC Technical Report: TR-CLMC-2007-2, University of Southern California",
  key =			 "relative entropy, policy search, natural policy gradient",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Peters-TR2007.pdf",
  note =		 "A longer and more complete version is under preparation.",
  crossref =		 "p10376"
}

@inproceedings{Peters_RSS_2006,
  author =		 "Peters, J. and Schaal, S.",
  year =		 "2006",
  title =		 "Learning operational space control",
  booktitle =		 "Robotics: Science and Systems (RSS 2006)",
  key =			 "operational space control redundancy forward models inverse models compliance reinforcement leanring locally weighted learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/p33.pdf",
  publisher =		 "cambridge, ma: mit press",
  crossref =		 "p2583"
}

@inproceedings{Peters_PIJCNN_2006,
  author =		 "Peters, J. and Schaal, S.",
  year =		 "2006",
  title =		 "Reinforcement Learning for Parameterized Motor Primitives",
  booktitle =		 "Proceedings of the 2006 International Joint Conference on Neural Networks (IJCNN)",
  key =			 "motor primitives, reinforcement learning",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JanPeters/Reinforcement_Learning_for_Parameterized_Motor_Pri.pdf",
  crossref =		 "p2656"
}

@inproceedings{Ting_RSS_2006,
  author =		 "Ting, J. and Mistry, M. and Nakanishi, J. and Peters, J. and Schaal, S.",
  year =		 "2006",
  title =		 "A Bayesian approach to nonlinear parameter identification for rigid body dynamics",
  booktitle =		 "Robotics: Science and Systems (RSS 2006)",
  key =			 "bayesian regression linear models dimensionality reduction input noise rigid body dynamics parameter identification",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/p32.pdf",
  publisher =		 "cambridge, ma: mit press",
  crossref =		 "p2582"
}

@inproceedings{IROS2006Peters_0,
  author =		 "Peters, J. and Schaal, S.",
  year =		 "2006",
  title =		 "Policy gradient methods for robotics",
  booktitle =		 "Proceedings of the IEEE International Conference on Intelligent Robotics Systems (IROS 2006)",
  key =			 "policy gradient methods, reinforcement learning, robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IROS2006-Peters_[0].pdf",
  crossref =		 "p2655"
}

@inproceedings{IROS2005Nakanishi_50510,
  author =		 "Nakanishi, J. and Cory, R. and Mistry, M. and Peters, J. and Schaal, S.",
  year =		 "2005",
  title =		 "Comparative experiments on task space control with redundancy resolution",
  booktitle =		 "IEEE International Conference on Intelligent Robots and Systems (IROS 2005)",
  key =			 "manipulator dynamicsredundant manipulatorsspace optimizationdynamical decouplinghumanoid robotsinverse kinematicsmotor coordinationredundancy resolutionrobot dynamicsseven-degree-of-freedom anthropomorphic robot armtask space controldynamical d",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IROS2005-Nakanishi_5051[0].pdf",
  crossref =		 "p2007"
}

@inproceedings{NaturalActorCritic,
  author =		 "Peters, J. and Vijayakumar, S. and Schaal, S.",
  year =		 "2005",
  title =		 "Natural Actor-Critic",
  booktitle =		 "Proceedings of the 16th European Conference on Machine Learning (ECML 2005)",
  key =			 "reinforcement learning, policy gradients, natural gradients",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/NaturalActorCritic.pdf",
  crossref =		 "p2574"
}

@inproceedings{PetMisUdwSchASME2005_50540,
  author =		 "Peters, J. and Mistry, M. and Udwadia, F. E. and Schaal, S.",
  year =		 "2005",
  title =		 "A new methodology for robot control design",
  booktitle =		 "The 5th ASME International Conference on Multibody Systems, Nonlinear Dynamics, and Control (MSNDC 2005)",
  key =			 "robot control, nonlinear control, gauss principle",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/PetMisUdwSchASME2005_5054[0].pdf",
  crossref =		 "p2575"
}

@inproceedings{IROS2005Peters_50520,
  author =		 "Peters, J. and Mistry, M. and Udwadia, F. E. and Cory, R. and Nakanishi, J. and Schaal, S.",
  year =		 "2005",
  title =		 "A unifying framework for the control of robotics systems",
  booktitle =		 "IEEE International Conference on Intelligent Robots and Systems (IROS 2005)",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IROS2005-Peters_5052[0].pdf",
  crossref =		 "p2576"
}

@inproceedings{Schaal2005_Chapter_LearningMovementPrimitives,
  author =		 "Schaal, S. and Peters, J. and Nakanishi, J. and Ijspeert, A.",
  year =		 "2004",
  title =		 "Learning Movement Primitives",
  booktitle =		 "International Symposium on Robotics Research (ISRR2003)",
  key =			 "movement primitives, supervised learning, reinforcment learning, locomotion, phase resetting, learning from demonstration",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/Schaal2005_Chapter_LearningMovementPrimitives.pdf",
  crossref =		 "p1805"
}

@inproceedings{Peters_PJSNC_2004,
  author =		 "Peters, J. and  Schaal, S.",
  year =		 "2004",
  title =		 "Learning Motor Primitives with Reinforcement Learning",
  booktitle =		 "Proceedings of the 11th Joint Symposium on Neural Computation",
  key =			 "natural policy gradients, motor primitives, natural actor-critic",
  crossref =		 "p10174"
}

@inproceedings{JSNC2003Mohajerian_0,
  author =		 "Mohajerian, P. and Peters, J. and Ijspeert, A. and Schaal, S.",
  year =		 "2003",
  title =		 "A unifying computational framework for optimization and dynamic systems approaches to motor control",
  booktitle =		 "Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003)",
  key =			 "computational motor control, optimization, dynamic systems, formal modeling",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/JSNC2003-Mohajerian_[0].pdf",
  crossref =		 "p1839"
}

@inproceedings{Peters_IICHR_2003,
  author =		 "Peters, J. and Vijayakumar, S. and Schaal, S.",
  year =		 "2003",
  title =		 "Reinforcement learning for humanoid robotics",
  booktitle =		 "IEEE-RAS International Conference on Humanoid Robots (Humanoids2003)",
  key =			 "reinforcement learning, policy gradients, movement primitives, behaviors, dynamic systems, humanoid robotics",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/JanPeters/peters-ICHR2003.pdf",
  crossref =		 "p1785"
}

@inproceedings{Peters_PJSNC_2003,
  author =		 "Peters, J. and Vijayakumar, S. and Schaal, S.",
  year =		 "2003",
  title =		 "Scaling reinforcement learning paradigms for motor learning",
  booktitle =		 "Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003)",
  key =			 "reinforcement learning, neurodynamic programming, actorcritic methods, policy gradient methods, natural policy gradient",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/petersVijayakumarSchaal_JSNC2003_5058[0].pdf",
  crossref =		 "p1838"
}

@inproceedings{IROS2003Schaal_0,
  author =		 "Schaal, S. and Peters, J. and Nakanishi, J. and Ijspeert, A.",
  year =		 "2003",
  title =		 "Control, planning, learning, and imitation with dynamic movement primitives",
  booktitle =		 "Workshop on Bilateral Paradigms on Humans and Humanoids, IEEE International Conference on Intelligent Robots and Systems (IROS 2003)",
  key =			 "movement primitives, supervised learning, reinforcment learning, locomotion, phase resetting, learning from demonstration",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/IROS2003-Schaal_[0].pdf",
  crossref =		 "p1804"
}

@inproceedings{Vijayakumar_ANIPSDT_2002,
  author =		 "Vijayakumar, S. and  D’Souza, A. and  Peters, J. and  Conradt, J. and  Rutkowski,T. and  Ijspeert, A. and  Nakanishi, J. and  Inoue, M. and  Shibata, T. and  Wiryo, A. and  Itti, L. and  Amari, S. and  Schaal, S",
  year =		 "2002",
  title =		 "Real-Time Statistical Learning for Oculomotor Control and Visuomotor Coordination",
  booktitle =		 "Advances in Neural Information Processing Systems (NIPS/NeurIPS), Demonstration Track",
  crossref =		 "p10778"
}

@techreport{techrep,
  author =		 "Peters, J.",
  year =		 "2002",
  title =		 "Policy Gradient Methods for Control Applications",
  booktitle =		 "CLMC Technical Report: TR-CLMC-2007-1, University of Southern California",
  URL =			 "https://www.ias.informatik.tu-darmstadt.de/uploads/Member/JanPeters/techrep.pdf",
  crossref =		 "p11165"
}

@inproceedings{burdet_ISHF_2001,
  author =		 "Burdet, E. and  Tee, K.P. and  Chew, C.M. and  Peters, J. and  Bt, V.L.",
  year =		 "2001",
  title =		 "Hybrid IDM/Impedance Learning in Human Movements",
  booktitle =		 "First International Symposium on Measurement, Analysis and Modeling of Human Functions Proceedings",
  key =			 "human motor control",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/burdet_ISHF_2001.pdf ",
  crossref =		 "p10104"
}

@inproceedings{peters_ICBME_2000,
  author =		 "Peters, J. and  Riener, R",
  year =		 "2000",
  title =		 "A real-time model of the human knee for application in virtual orthopaedic trainer",
  booktitle =		 "Proceedings of the 10th International Conference on Biomedical Engineering Conference (ICBME)",
  key =			 "biomechanics, human motor control",
  URL =			 "http://www.ias.informatik.tu-darmstadt.de/uploads/Publications/peters_ICBME_2000.pdf",
  crossref =		 "p10106"
}

@article{Peters_KI_1998,
  author =		 "Peters, J.",
  year =		 "1998",
  title =		 "Fuzzy Logic for Practical Applications",
  booktitle =		 "Kuenstliche Intelligenz (KI)",
  key =			 "book review",
  number =		 "4",
  pages =		 "60",
  crossref =		 "p10134"
}