Main » Curriculum Vitae

Research Statement
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can learn a multitude of different tasks, triggered by environmental context or higher level instruction. Achieving this goal requires the development of novel machine learning methods for model-, imitation and reinforcement learning that scale into the domain of humanoid robotics. In order to achieve this goal, we also rely both on the proper evaluation of robot skill execution from a traditional control perspective as well as on insights into analytical mechanics and human motor control.

Current Position
Senior Research Scientist, Head of the Robot Learning Group
Dept. Empirical Inference (Dept.Head: Bernhard Schoelkopf), Max Planck Institute for Biological Cybernetics, Tuebingen, Germany

Educational Background
2001-2007Ph.D. in Computer Science
 University of Southern California, Los Angeles, CA, USA
 Thesis Title: Machine Learning for Motor Skills in Robotics
 Defended on March 21, 2007
 Thesis Committee: Stefan Schaal, Gaurav Sukhatme, Firdaus Udwadia, Chris Atkeson (CMU)
2004-2005M.Sc. in Aerospace & Mechanical Engineering (Dynamics & Control)
 University of Southern California, Los Angeles, CA, USA
2001-2002M.Sc. in Computer Science
 University of Southern California, Los Angeles, CA, USA
1996-2002Diplom-Ingenieur (German M.Eng. in Electrical Engineering)
 Munich University of Technology, Munich, Germany
2000-2001Visiting graduate student
 National University of Singapore, Singapore
1996-2000Diplom-Informatiker (German M.Sc. in Computer Science)
 Hagen University, Hagen, Germany
 Thesis Title: Neural Networks in Robot Control
 Thesis Committee: Patrick van der Smagt (DLR), Gerd Hirzinger (DLR), Christoph Beierle (U.Hagen)
 
Research Positions
2009-nowSenior Research Scientist, Head of the Robot Learning Group
 Dept. Empirical Inference (Dept.Head: Bernhard Schoelkopf), Max Planck Institute for Biological Cybernetics, Tuebingen, Germany
2007-2009Research Scientist, Head of the Robot Learning Group
 Dept. Empirical Inference (Dept.Head: Bernhard Schoelkopf), Max Planck Institute for Biological Cybernetics, Tuebingen, Germany
2001-2007Research Assistant
 Computational Learning and Motor Control Lab (Head: Stefan Schaal), University of Southern California, Los Angeles, CA, USA
2003Visiting Researcher
 Department of Humanoid Robotics (Head: Gordon Cheng), Advanced Telecommunication Research Center ATR, Kyoto
2001Visiting Researcher
 National University of Singapore, Singapore
2000Visiting Researcher
 Cyberhuman Project (Head: Mitsuo Kawato), Advanced Telecommunication Research Center ATR, Kyoto, Japan
2000Student Researcher
 Institute of Automatic Control Engineering, Munich University of Technology, Munich, Germany
1998-2000Student Researcher
 Institute of Robotics and Mechatronics of the German Aerospace Research Institute DLR, Oberpfaffenhofen, Germany
 
Teaching
2007Lecturer, Summer School Course: Policy Learning for Robotics
 IEEE-RAS / IFRR School of Robotics Science on Learning [link]
2006Lectures on Policy Gradient Methods, Graduate course: CS 599 Robot Learning
 University of Southern California, Los Angeles, CA, USA
2004Teaching Assistant, Graduate course: CS 545 Robotics
 University of Southern California, Los Angeles, CA, USA
2003Teaching Assistant, Graduate course: CS 545 Robotics
 University of Southern California, Los Angeles, CA, USA
1997-1998Lab Assistant, Undergraduate course: Informatik Praktikum
 Lehrstuhl fuer Datenverarbeitung, Munich University of Technology, Munich, Germany
 
Industrial Experience
2000Internship at Siemens Advanced Engineering Ltd.
 Singapore
1998Internship at Siemens AG
 Munich, Germany
1997Internship at Siemens AG
 Munich, Germany
1996Internship at Germanischer Lloyd AG
 Hamburg, Germany
1992-1993Software Development for Noelting Gmbh
 Hamburg, Germany
1992Internship at Philips Consumer Electronics Gmbh
 Hamburg, Germany
 
Technical Committee Organisation
2008-nowIEEE Technical Committee on Robotics and Machine Learning [link]
 Chair together with Nick Roy (MIT), Russ Tedrake (MIT), Jun Morimoto (ATR). All are also founding chairs.
 
Community Services
2007-nowAdministration of the mailing list ROBOTICS-WORLDWIDE (currently the most important robotics mailing list) together with Stefan Schaal (USC) and Michael Mistry (USC).
 
Editing
2008-2009Autonomous Robots - Special Issue on Robot Learning [link]
 Editor together with Andrew Y. Ng (Stanford University)
2008-2009From motor to interaction learning in robots, Edited Book in Springer Verlag.
 Editor together with Olivier Sigaud (U. Paris 6)
 
Conference and Workshop Organization
6/2009RSS 2009 Workshop: Bridging the gap between high-level discrete representations and low-level continuous behaviors with Dana Kulic, (U.Tokyo/U. Waterloo) and Pieter Abbeel (U.California in Berkeley).
5/2009ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots
 Co-Organizer of Ales Ude (Josef Stefan Institute), Tamim Asfour (U. Karlsruhe), Jun Morimoto (ATR) and Stefan Schaal (USC)
9/2008IROS 2008 Workshop: Robotics Challenges for Machine Learning II
 Co-Organizer of Russ Tedrake (MIT), Nick Roy (MIT) and Jun Morimoto (ATR)
9/2008IROS 2008 Workshop: From motor to interaction learning in robots [link]
 Co-Organizer of Olivier Sigaud (U.Paris 6) and Sethu Vijayakumar (U.Edingburgh)
7/2008The 6th International Cognitive Robotics Workshop (aka the ECAI 2008 Workshop on Cognitive Robotics) [link]
 Co-Organizer of Yves Lespérance (U.York), Gerhard Lakemeyer (RWTH Aachen) and Fiora Pirri (U. Rome)
12/2007NIPS 2007: Robotics Challenges for Machine Learning [link]
 Organizing it together with my co-organizer Marc Toussaint (TU Berlin) at the NIPS 2007 conference [link].
7-8/2007PASCAL Workshop: Analysis of reinforcement learning problems
 Co-Organizer of Peter Auer (U.Leoben)
12/2006NIPS 2006: Towards a new reinforcement learning? [link]
 Organizing it together with my co-organizers Drew Bagnell (CMU) and Stefan Schaal (USC) at the NIPS 2006 conference [link].
6/2005RSS 2005: Learning for Locomotion Workshop [link]
 Organizing it together with my co-organizers Russ Tedrake (MIT) and Stefan Schaal (USC) at the Robotics 2005 conference [link].
11/2004IEEE International Conference on Humanoid Robotics (HUMANOIDS 2004) [link]
 Local arrangements with Stefan Schaal, Aaron D'Souza and Peyman Mohajerian
 
External Thesis Committee
11/28/2008External Member of Ruben Martinez-Cantin's thesis committee, thesis titled Active Map Learning: Insights into Statistical Consistency at University of Zaragoza.
3/1/2009External Evaluator of Diego Pardo's thesis committee, thesis titled LEARNING REST-TO-REST MOTOR COORDINATION IN ARTICULATED MOBILE ROBOTS at the Technical University of Catalonia.
 
Program/Scientific Committee of Conferences/Workshops
2009International Conference for Robotics and Automation (ICRA), Associate Editor (AE) for "Learning and Adaptive Systems"
 18th IEEE International Symposium on Robot and Human Interactive Communication RO-MAN (Associate Editor, IPC)
 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems LAB-RS 2009 (Program Committee)
 Workshop on Abstractions in Reinforcement Learning (Program Committee)
 International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems 2009 (ERLARS, Program Committee)
 International Workshop on Hybrid Control of Autonomous Systems (HYCAS, Program Committee)
 International Conference on Machine Learning (ICML, Program Committee)
International Joint Conference on Artificial Intelligence (IJCAI, Program Committee)
2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL,Program Committee)
25th Conference on Uncertainty in Artificial Intelligence (UAI,Program Committee)
International Conference on Development and Learning (ICDL,Program Committee)
First International Workshop on LEarning and data Mining for Robotics (LEMIR 2009)
International Workshop on Hybrid Control of Autonomous Systems (HYCAS,Program Committee)
Robotics: Science & Systems R:SS (Program Committee)
ICML Workshop on Abstractions in Reinforcement Learning (Program Committee)l
2008Robotics: Science & Systems R:SS (Program Committee)
 Cognitive Information Processing Workshop CIP (Scientific Committee)
Twenty-Third AAAI Conference on Artificial Intelligence (Program Committee of both Main Conference and the physically grounded track)
International Conference on the Simulation of Adaptive Behavior SAB (Program Committee)
International Conference on Cognitive Systems CogSys 2008 (Program Committee)
European Workshop on Reinforcement Learning EWRL (Program Committee)
17th IEEE International Symposium on Robot and Human Interactive Communication RO-MAN (Associate Editor, IPC)
ERLARS (Program Committee)
ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems LAB-RS 2008 (Program Committee)
2006International Conference on Machine Learning (ICML, Program Committee)
2005Robotics: Science & Systems (R:SS, Program Committee)
 
Plenary talks and Invited talks at Workshops & Conferences
6/29/2009Invited talk Skill Learning with the Barrett WAM at the RSS Workshop on Creative Manipulation: Examples using the WAM].
6/28/2009Invited talk Reward-Weighted Regression for Reinforcement Learning at the RSS Workshop on Regression in Robotics - Approaches and Applications.
5/24/2009Invited plenary lecture at 4th XVR Workshop & Joint PRESENCCIA and SKILLS PhD Symposium.
10/24/2008Invited plenary lecture at Premières Journées Annuelles du GDR Robotique 2008 (French National Conference on Robotics)
9/26/2008Invited talk Motor Skill Learning at IROS 2008 Workshop: From motor to interaction learning in robots
7/22/2008Invited plenary lecture/Keynote Motor Skill Learning for Cognitive Robotics at Cognitive Robotics 2008. Joint keynote of the ERLARS Workshop.
7/3/2008Invited plenary lecture/Keynote Reinforcement Learning for Robotics at the European Workshop on Reinforcement Learning (EWRL).
6/28/2008Keynote Motor Skill Learning at the Robotics: Science & Systems (R:SS), Workshop on Interactive Robotic Learning.
6/11/2005Invited talk Learning Motor Primitives with Reinforcement Learning at Robotics: Science & Systems (R:SS), Workshop on Modular Foundations for Control and Perception
5/23/2005Invited plenary lecture Motor Skills Learning for Humanoid Robots at the First Undergraduate Computer Sciences and Informations Sciences (CS/IS) conference.
 
Invited talks at Labs
4/16/2009Invited Talk Robot Policy Learning, Informatik Kolloqium, Host: G. Lakemeyer, RWTH Aachen, Germany
11/27/2008Invited Talk Policy Learning in Robotics, Host: J.A. Castellano, University of Zaragoza
11/4/2008Invited Talk Skill Learning for Humanoid Robotics, Host: M. Gienger, Honda Research International, Offenbach
11/3/2008Invited Talk Machine Learning Applications in Robotics, Host: M.Riedmiller, University of Osnabrueck
10/8/2008Invited Talk Machine Learning for Robotics, Host: K.-R. Mueller, Frauenhofer FIRST IDA, Berlin
2/13/2008Invited Talk Towards Motor Skill Learning in Robotics, Host: A.Zell, University of Tuebingen
11/21/2007Invited Talk Motor Skills Learning for Robotics, Host: T.Nakamura, Yamane-Nakamura Lab, The University of Tokyo, Tokyo, Japan
11/20/2007Invited Talk Machine Learning of Motor Skills, Host: M. Sugiyama, Tokyo Institute of Technology (TIT), Tokyo, Japan
11/16/2007Invited Talk Learning Motor Skills, Host: G.Cheng, Advanced Telecommunications Research Center (ATR), Kyoto, Japan
11/12/2007Invited Learning Motor Skills, Host: T.Shibata, Nara Institute of Science and Technology (NAIST), Nara, Japan
9/21/2007Invited Talk Learning for Motor Control, ISR, Hosts: I. Ribero, M. Lopes, ISR, Instituto Superior Technical (IST), Lisbon, Portugal
9/20/2007Invited Talk Learning Operational Space Control, ISR, Host: R. Cortesao, ISR, University of Coimbra, Coimbra, Portugal
6/12/2007Invited Talk Robot Skill Learning, TAMS, Host: J. Zhang, University of Hamburg, Hamburg, Germany
5/22/2007Invited talk Towards Motor Skills Learning in Robotics, IAIM, Hosts: R.Dillman & T. Asfour, University of Karlsruhe (TH), Karlsruhe, Germany
12/14/2006Invited talk Towards Motor Skills Learning in Robotics, Host: B. Schoelkopf, Max-Planck Institute for Biological Cybernetics (MPI), Tuebingen, Germany
12/1/2006Invited talk Towards Motor Skills Learning in Robotics, Hosts: J. Schmidthuber, M.Beetz, Munich University of Technology, Germany
11/30/2006Invited talk Towards Motor Skills Learning in Robotics, Host: J. Schmidthuber, Instituto Dalle Molle di Studi sull'Intelligenza Artificiale IDSIA, Lugano, Switzerland
11/13/2006Invited talk Towards Motor Skills Learning in Robotics, Host: A. Ng, PAIL Series, SAIL AI Lab, Stanford University
6/9/2005Invited talk Learning Motor Primitives with Reinforcement Learning at the The Seung Lab, Host: R. Tedrake, Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology (MIT)
3/9/2004Invited talk Reinforcement Learning: neurobiology and methodology guest lecture for CS 499 Exotic Computation invited by M. Arbib.
10/5/2003Invited talk Reinforcement Learning for Humanoid Robotics at Robotics & Mechatronics Institute, Host: P. van der Smagt, German Aerospace Research Center (DLR).
7/28/2003Invited talk Natural Actor-Critic at Nara Institute of Science and Technology (NAIST), Host: Shin Ishi.
7/17/2003Invited talk Natural Actor-Critic at the Advanced Telecommunications Research Center (ATR), Host: Gordon Cheng
 
Oral Conference and Workshop Presentations
5/17/2009Workshop presentation Learning to Bridge the GAP with Motor Primitives at Bridging the gap between high-level discrete representations and low-level continuous behaviors.
5/17/2009Workshop presentation Reinforcement learning for Sensory-Motor Control at ICRA 2009 Workshop: Approaches to Sensorimotor Learning on Humanoid Robots.
9/22/2008Workshop presentation Policy Learning for Robotics: a Unified Perspective at IROS 2008 Workshop: Robotics Challenges for Machine Learning II.
5/23/2008Conference presentation Learning resolved velocity control at IEEE Conference on Robotics and Automation (ICRA).
11/14/2007Conference presentation Policy Learning for Robotics at the International Conference on Neural Information Processing (ICONIP)
10/19/2007Conference presentation Towards Motor Skill Learning at the Fachgespraech Autonome Mobile Systeme
6/22/2007Conference presentation Reinforcement Leaning by Reward-Weighted Regression at International Conference on Machine Learning (ICML)
4/26/2007Conference presentation Applying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning at the European Symposium on Artificial Neural Networks (ESANN 2007).
4/12/2007Conference presentation Reinforcement Learning for Operational Space Control at IEEE Conference on Robotics and Automation (ICRA).
4/4/2007Workshop presentation Using Reward-Weighted Regression for Reinforcement Learning of Task Space Control at the ADPRL 2007 Workshop
4/4/2007Workshop presentation Benchmarking of Policy Gradient Methods at the ADPRL 2007 Workshop
12/8/2006Workshop presentation Reward-Weighted Regression for Reinforcement Learning at NIPS 2006 Workshop
10/12/2006Conference presentation Policy Gradient Methods for Robotics at IEEE/RSJ Conference on Intelligent Robots and Systems (IROS).
10/5/2005Conference presentation Natural Actor-Critic at 16th European Conference on Machine Learning.
9/26/2005Conference presentation A new methodology for robot controller design at ASME IDECT 5th International Conference on Multibody Systems, Nonlinear Dynamics, and Control (ASME MSNDC).
8/5/2005Conference presentation A Unifying Framework for the Control of Robotic Systems at IEEE/RSJ Conference on Intelligent Robots and Systems (IROS).
10/22/2004Workshop presentation Learning Motor Primitives with Reinforcement Learning at the AAAI Workshop on Real Life Reinforcement Learning.
12/13/2003Workshop presentation Learning Control and Planning from the View of Control Theory and Imitation with S.Schaal at NIPS Workshop on Planning for the Real World: The promises and challenges of dealing with uncertainty.
12/12/2003Workshop presentation Recurrent neural networks from learning attractor dynamics with S.Schaal at NIPS Workshop on RNNaissance: Recurrent Neural Networks.
10/2/2003Conference presentation Reinforcement Learning for Humanoid Robotics at IEEE International Conference on Humanoid Robotics.
12/6/2000Conference presentation A Real Time Model of the Human Knee for a Virtual Orthopaedic Trainer at International Conference on Biomedical Engineering
 
Position Statements
9/4/2008Position statement Machine Learning for Cognitive and Intelligent Systems at Third Interlink-Workshop on Intelligent Cognitive Systems, Santa Monica, CA, USA, 4-5 September 2008.
 
Awards and Honors
2008IROS 2008 Best Paper Award Finalist for Nguyen, D.; Peters, J. (2008). Local Gaussian Processes Regression for Real-time Model-based Robot Control, International Conference on Intelligent Robot Systems (IROS)
2006National Science Foundation Travel Fellowship for IROS 2006 in Beijing, China
2001-2004University of Southern California Presidential Fellowship, accepted.
2001-2004Carnegie Mellon University Doctoral Fellowship, declined.
2000-2002Siemens Student Scholarship (SSP)
2000-2001Munich University of Technology's Singapore Scholarship
1994-1995Finalist in the 14. Bundeswettbewerb Informatik (German National Computer Science Competition)
1993-1994Finalist & St. Augustin Award in the 13. Bundeswettbewerb Informatik (German National Computer Science Competition)
 
Paper Reviewing
200912th International Conference on Artificial Intelligence and Statistics (AISTATS 2009)
 International Conference on Robotic Systems (IROS)
 International Symposium on Robotics Research (ISRR), Advances in Neural Information Processing Systems (NIPS)
2008Advances in Neural Information Processing Systems (NIPS)
 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI 2009)
Applied Mathematics and Computation Journal
International Conference on Cognitive Systems (CogSys 2008)
Autonomous Robots Journal
Robotics: Science & Systems (R:SS 2008)
17th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)
Twenty-Third AAAI Conference on Artificial Intelligence (AAAI 2008)
International Conference on the Simulation of Adaptive Behavior (SAB 2008)
The Snowbird Workshop
International Journal of Robotics Research (IJRR)
Neurocomputing
European Workshop on Reinforcement Learning (EWRL 2008)
IEEE Transactions on Robotics
Cambridge University Press (Book Proposal Evaluation)
2007Advances in Neural Information Processing Systems (NIPS)
 International Conference on Neural Information Processing (ICONIP)
International Joint Conference on Neural Networks
IEEE International Symposium on Industrial Electronics
Neural Networks
Automatica
European Symposium on Artificial Neural Networks
International Journal of Robotics Research
Artificial Intelligence Journal
Electronics Letters
IEEE Conference on Decision and Control (CDC)
International Conference on Robotic Systems (IROS)
Adaptive Behavior
Artificial Intelligence Review
IEEE International Conference on Robotics and Automation (ICRA)
IEEE Transactions on Systems, Man and Cybernetics - Part B
Neurocomputing
Neural Computation
Advanced Robotics
2006IEEE Robotics & Automation Society Magazine
 Journal of Artificial Intelligence Research
IEEE International Conference on Robotics and Automation (ICRA)
International Conference on Machine Learning (ICML)
Advances in Neural Information Processing Systems (NIPS)
2005IEEE Transactions on Neural Networks
 Mathematical Problems in Engineering
International Conference on Machine Learning (ICML)
Advances in Neural Information Processing Systems (NIPS)
International Conference on Robotic Systems (IROS)
Robotics: Science & Systems (RSS)
Autonomous Robots
2004International Conference on Machine Learning (ICML)
 Advances in Neural Information Processing Systems (NIPS)
International Conference on Robotic Systems (IROS)
IEEE Transactions on Robotics and Automation
2002IEEE International Conference on Robotics and Automation (ICRA)
 IEEE Transactions on Robotics and Automation
2001IEEE Transactions on Neural Networks
 Journal of Neurophysiology
2000International Journal of Applied Intelligence
 
International Proposal Reviewing
2008NWO Physical Sciences
2007STW Dutch Technology Foundation
 
References, etc.
References are available upon request, and for coursework see here.
 
Books & Theses

Peters, J.; Tedrake, R.; Roy, N.; Morimoto, J. (in press). Robot Learning, Encyclopedia of Machine Learning.

Sigaud, O.; Peters, J. (in press). Robot Learning, Encyclopedia of the Sciences of Learning, Springer Verlag, Seel, Norbert M..

Peters, J.; Bagnell, J.A. (in press). Policy gradient methods, Encyclopedia of Machine Learning (invited article). [PDF]

Nguyen-Tuong, D.; Seeger, M.; Peters, J. (2010). Real-Time Local GP Model Learning, From Motor Learning to Interaction Learning in Robots, Springer Verlag, 264.

Sigaud, O.; Peters, J. (2010). From Motor Learning to Interaction Learning in Robots, Studies in Computational Intelligence, Springer Verlag, 264.

Kober,J.; Mohler, B.; Peters, J. (2010). Imitation and Reinforcement Learning for Motor Primitives with Perceptual Coupling, From Motor Learning to Interaction Learning in Robots, Springer Verlag.

Detry,R.; Baseski, E.; Popovic, M.; Touati, Y.; Krueger, N.; Kroemer, O.; Peters, J.; Piater, J. (2010). Learning Continuous Grasp Affordances by Sensorimotor Exploration, From Motor Learning to Interaction Learning in Robots, Springer Verlag, 264.

Lesperance, Y.; Lakemeyer, G.; Peters, J.; Pirri, F. (2008). Proceedings of the 6th International Cognitive Robotics Workshop (CogRob 2008), July 21-22, 2008, Patras, Greece, ISBN 978-960-6843-09-9.

Peters, J. (2008). Machine Learning for Robotics, VDM-Verlag, ISBN 978-3-639-02110-3. [PDF]

Peters, J. (2007). Machine Learning of Motor Skills for Robotics, Ph.D. Thesis, Department of Computer Science, University of Southern California.
[Keywords: Machine Learning, Reinforcement Learning, Robotics, Motor Primitives, Policy Gradients, Natural Actor-Critic, Reward-Weighted Regression]

 
Journal Papers

Wierstra, D.; Foerster, A.; Peters, J.; Schmidhuber, J. (in press). Recurrent Policy Gradients, Logic Journal of the IGPL.

Sehnke, F.; Osendorfer, C.; Rueckstiess, T.; Graves, A.; Peters, J.; Schmidhuber, J. (in press). Parameter-exploring Policy Gradients, Neural Networks.

Morimura, T.; Uchibe, E.; Yoshimoto, J.; Peters, J.; Doya, K. (2010). Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning, Neural Computation, 22, 2.

Hachiya,H.; Akiyama, T.; Sugiyama, M.; Peters, J. (2009). Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning, Neural Networks, 22, 10, pp.1399-1410.
[Keywords: off-policy reinforcement learning; value function approximation; policy iteration; adaptive importance sampling; importance-weighted cross-validation; efficient sample reuse]

Deisenroth, M.P., Rasmussen, C.E.; Peters, J (2009). Gaussian Process Dynamic Programming, Neurocomputing, 72, pp.1508-1524.

Peters, J.; Ng, A. (2009). Guest Editorial: Special Issue on Robot Learning, Part B, Autonomous Robots, 27, 2.

Nguyen-Tuong, D.; Seeger, M.; Peters, J. (2009). Model Learning with Local Gaussian Process Regression, Advanced Robotics, 23, 15, pp.2015-2034.

Kober, J.; Peters, J. (2009). Reinforcement Learning fuer Motor-Primitive, Kuenstliche Intelligenz.

Peters, J.; Morimoto, J.; Tedrake, R.; Roy, N. (2009). Robot Learning, IEEE Robotics & Automation Magazine, 16, 3, pp.19-20.
[Keywords: robot learning, tc spotlight]

Peters, J.; Ng, A. (2009). Guest Editorial: Special Issue on Robot Learning, Part A, Autonomous Robots, 27, 1.

Steinke, F.; Hein, M.; Peters, J.; Schoelkopf, B (2008). Manifold-valued Thin-Plate Splines with Applications in Computer Graphics, Computer Graphics Forum (Special Issue on Eurographics 2008), 27, 2. [PDF]

Nakanishi, J.;Cory, R.;Mistry, M.;Peters, J.;Schaal, S. (2008). Operational space control: A theoretical and emprical comparison, International Journal of Robotics Research, 27, 6, pp.737-757.
[Keywords: task space control, operational space control, redundancy resolution, humanoid robotics] [PDF]

Peters, J. (2008). Machine Learning for Motor Skills in Robotics, Kuenstliche Intelligenz, 3.
[Keywords: motor control, motor primitives, motor learning] [PDF]

Peters, J.;Schaal, S. (2008). Natural actor critic, Neurocomputing, 71, 7-9, pp.1180-1190.
[Keywords: reinforcement learning, policy gradient, natural actor-critic, natural gradients] [PDF]

Peters, J.;Schaal, S. (2008). Learning to control in operational space, International Journal of Robotics Research, 27, pp.197-212.
[Keywords: operational space control, learning, EM ALGORITHM, redundancy resolution, reinforcement learning] [PDF]

Peters, J.;Schaal, S. (2008). Reinforcement learning of motor skills with policy gradients, Neural Networks, 21, 4, pp.682-97.
[Keywords: Reinforcement learning, Policy gradient methods, Natural gradients, Natural Actor-Critic, Motor skills, Motor primitives] [PDF]

Peters, J.;Mistry, M.;Udwadia, F. E.;Nakanishi, J.;Schaal, S. (2008). A unifying methodology for robot control with redundant DOFs, Autonomous Robots, 24, 1, pp.1-12.
[Keywords: operational space control, inverse control, dexterous manipulation, optimal control] [PDF]

Peters, J. (2007). Computational Intelligence: By Amit Konar, The Computer Journal, 50, 6, pp.758.
[Keywords: book review]

Peters, J. (1998). Fuzzy Logic for Practical Applications, Kuenstliche Intelligenz (KI), 4, pp.60.
[Keywords: book review]

 
Conference and Workshop Papers

Nguyen-Tuong, D.; Peters, J. (2010). Incremental Sparsification for Real-time Online Model Learning, Proceedings of Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010).

Kober,J.; Muelling,K.; Kroemer, O.; Lampert,C.H.; Schoelkopf, B.; Peters, J. (2010). Movement Templates for Learning of Hitting and Batting, IEEE International Conference on Robotics and Automation.

Nguyen-Tuong, D.; Peters, J. (2010). Using Model Knowledge for Learning Inverse Dynamics, IEEE International Conference on Robotics and Automation.

Hachiya, H.; Peters, J.; Sugiyama, M. (2009). Efficient Sample Reuse in EM-based Policy Search, Proceedings of the 16th European Conference on Machine Learning (ECML 2009).

Peters, J.; Kober, J.; Muelling, K.; Nguyen-Tuong, D.; Kroemer, O. (2009). Towards Motor Skill Learning for Robotics, Proceedings of the International Symposium on Robotics Research (ISRR), Invited Paper.

Nguyen-Tuong, D.; Seeger, M.; Peters, J. (2009). Local Gaussian Process Regression for Real Time Online Model Learning and Control, Advances in Neural Information Processing Systems 22 (NIPS 2008), Cambridge, MA: MIT Press. [PDF]

Neumann, G.; Peters, J. (2009). Fitted Q-iteration by Advantage Weighted Regression, Advances in Neural Information Processing Systems 22 (NIPS 2008), Cambridge, MA: MIT Press. [PDF]

Kober, J.; Peters, J. (2009). Policy Search for Motor Primitives in Robotics, Advances in Neural Information Processing Systems 22 (NIPS 2008), Cambridge, MA: MIT Press. [PDF]

Chiappa, S.; Kober, J.; Peters, J. (2009). Using Bayesian Dynamical Systems for Motion Template Libraries, Advances in Neural Information Processing Systems 22 (NIPS 2008), Cambridge, MA: MIT Press. [PDF]

Hoffman, M.; de Freitas, N. ; Doucet, A.; Peters, J. (2009). An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward, Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AIStats).

Peters, J.; Kober, J. (2009). Using Reward-Weighted Imitation for Robot Reinforcement Learning, Proceedings of the 2009 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning..

Hachiya, H.; Akiyama, T.; Sugiyama, M.; Peters, J. (2009). Efficient Data Reuse in Value Function Approximation, Proceedings of the 2009 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning..

Kober, J.; Peters, J. (2009). Learning Motor Primitives for Robotics, Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).

Piater, J.; Jodogne, S.; Detry, R.; Kraft, D.; Krueger, N.; Kroemer, O.; Peters, J. (2009). Learning Visual Representations for Interactive Systems, Proceedings of the International Symposium on Robotics Research (ISRR), Invited Paper.

Kober, J., and Peters, J. (2009). Learning Motor Primitives for Robotics, Proceedings of Autonome Mobile Systeme (AMS 2009).

Muelling, K., and Peters, J. (2009). A computational model of human table tennis for robot application, Proceedings of Autonome Mobile Systeme (AMS 2009).

Kroemer, O., Detry, R., Piater, J., and Peters, J. (2009). Active Learning Using Mean Shift Optimization for Robot Grasping, Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009).

Nguyen-Tuong, D., Schoelkopf, B., and Peters, J. (2009). Sparse Online Model Learning for Robot Control with Support Vector Regression, Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009).

Sigaud, O.; Peters, J. (2009). From Motor Learning to Interaction Learning in Robots, Proceedings of Journees Nationales de la Recherche en Robotique.

Neumann, G.; Maass, W; Peters, J. (2009). Learning Complex Motions by Sequencing Simpler Motion Templates, Proceedings of the International Conference on Machine Learning (ICML2009).

Detry, R; Baseski, E.; Popovic, M.; Touati, Y.; Krueger, N; Kroemer, O.; Peters, J.; Piater, J; (2009). Learning Object-specific Grasp Affordance Densities, Proceedings of the International Conference on Development & Learning (ICDL 2009).

Lampert, C.H.; Peters, J. (2009). Active Structured Learning for High-Speed Object Detection, Proceedings of the DAGM (Pattern Recognition).

Deisenroth, M.; Peters, J.; Rasmussen, C. (2008). Approximate Dynamic Programming with Gaussian Processes, American Control Conference. [PDF]

Nguyen-Tuong, D.; Peters, J.; Seeger, M.; Schoelkopf, B. (2008). Computed Torque Control with Nonparametric Regressions Techniques, American Control Conference. [PDF]

Deisenroth, M.P., Rasmussen, C.E.; Peters, J (2008). Model-Based Reinforcement Learning with Continuous States and Actions, Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008). [PDF]

Nguyen-Tuong, D.; Peters, J.; Seeger, M.; Schoelkopf, B. (2008). Learning Inverse Dynamics: a Comparison, Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008). [PDF]

Peters, J.; Nguyen-Tuong, D. (2008). Real-Time Learning of Resolved Velocity Control on a Mitsubishi PA-10, International Conference on Robotics and Automation (ICRA). [PDF]

Hachiya, H.; Akiyama, T.; Sugiyama, M.; Peters, J. (2008). Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation, Proceedings of the Twenty-Third National Conference on Artificial Intelligence (AAAI 2008). [PDF]

Wierstra,D.; Schaul,T.; Peters, J.; Schmidhuber, J. (2008). Natural Evolution Strategies, 2008 IEEE Congress on Evolutionary Computation. [PDF]

Nguyen-Tuong, D.; Peters, J. (2008). Local Gaussian Processes Regression for Real-time Model-based Robot Control, International Conference on Intelligent Robot Systems (IROS). [PDF]

Kober, J.; Mohler, B.; Peters, J. (2008). Learning Perceptual Coupling for Motor Primitives, International Conference on Intelligent Robot Systems (IROS). [PDF]

Wierstra, D.; Schaul, T.; Peters, J.; Schmidthuber, J. (2008). Fitness Expectation Maximization, 10th International Conference on Parallel Problem Solving from Nature (PPSN 2008). [PDF]

Wierstra,D.; Schaul,T.; Peters, J.; Schmidhuber, J. (2008). Episodic Reinforcement Learning by Logistic Reward-Weighted Regression, Proceedings of the International Conference on Artificial Neural Networks (ICANN). [PDF]

Sehnke, F.; Osendorfer, C; Rueckstiess, T; Graves, A.; Peters, J.; Schmidhuber, J. (2008). Policy Gradients with Parameter-based Exploration for Control, Proceedings of the International Conference on Artificial Neural Networks (ICANN). [PDF]

Peters, J.; Kober, J.; Nguyen-Tuong, D. (2008). Policy Learning – a unified perspective with applications in robotics, Proceedings of the European Workshop on Reinforcement Learning (EWRL).
[Keywords: reinforcement learning, policy gradient, weighted regression] [PDF]

Kober, J.; Peters, J. (2008). Reinforcement Learning of Perceptual Coupling for Motor Primitives, Proceedings of the European Workshop on Reinforcement Learning (EWRL).

Nguyen-Tuong, D.; Peters, J. (2008). Learning Robot Dynamics for Computed Torque Control using Local Gaussian Processes Regression, Proceedings of the ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, LAB-RS 2008. [PDF]

Peters, J., Schaal, S. (2007). Policy Learning for Motor Skills, Proceedings of 14th International Conference on Neural Information Processing (ICONIP).
[Keywords: Machine Learning, Reinforcement Learning, Robotics, Motor Primitives, Policy Gradients, Natural Actor-Critic, Reward-Weighted Regression] [PDF]

Wierstra, D.; Foerster, A.; Peters, J.; Schmidhuber, J. (2007). Solving Deep Memory POMDPs with Recurrent Policy Gradients, Proceedings of the International Conference on Artificial Neural Networks (ICANN).
[Keywords: policy gradients, reinforcement learning] [PDF]

Peters, J.; Schaal, S.; Schoelkopf, B. (2007). Towards Machine Learning of Motor Skills, Proceedings of Autonome Mobile Systeme (AMS).
[Keywords: Motor Skill Learning, Robotics, Natural Actor-Critic, Reward-Weighted Regeression] [PDF]

Theodorou, E; Peters, J; Schaal, S. (2007). Reinforcement Learning for Optimal Control of Arm Movements, Abstracts of the 37st Meeting of the Society of Neuroscience..
[Keywords: Optimal Control,Reinforcement Learning, Arm Movements]

Nakanishi, J.;Mistry, M.;Peters, J.;Schaal, S. (2007). Experimental evaluation of task space position/orientation control towards compliant control for humanoid robots, IEEE International Conference on Intelligent Robotics Systems (IROS 2007).
[Keywords: operational space control, quaternion, task space control, resolved motion rate control, resolved acceleration, force control] [PDF]

Peters, J.;Schaal, S. (2007). Reinforcement learning for operational space control, International Conference on Robotics and Automation (ICRA2007), pp.2111-2116.
[Keywords: operational space control, reinforcement learning, weighted regression, EM-Algorithm] [PDF]

Peters, J.;Schaal, S. (2007). Using reward-weighted regression for reinforcement learning of task space control, Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning.
[Keywords: reinforcement learning, cart-pole, policy gradient methods] [PDF]

Peters, J.;Schaal, S. (2007). Applying the episodic natural actor-critic architecture to motor primitive learning, Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN).
[Keywords: reinforcement learning, policy gradient methods, motor primitives, natural actor-critic] [PDF]

Peters, J.;Schaal, S. (2007). Reinforcement learning by reward-weighted regression for operational space control, Proceedings of the International Conference on Machine Learning (ICML2007).
[Keywords: reinforcement learning, operational space control, weighted regression] [PDF]

Peters, J.;Theodorou, E.;Schaal, S. (2007). Policy gradient methods for machine learning, INFORMS Conference of the Applied Probability Society.
[Keywords: policy gradient methods, reinforcement learning, simulation-optimization]

Riedmiller, M.;Peters, J.;Schaal, S. (2007). Evaluation of policy gradient methods and variants on the cart-pole benchmark, Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning.
[Keywords: reinforcement learning, cart-pole, policy gradient methods] [PDF]

Peters, J.;Schaal, S. (2006). Learning operational space control, in: Burgard, W.;Sukhatme, G. S.;Schaal, S. (eds.), Robotics: Science and Systems (RSS 2006), Cambridge, MA: MIT Press.
[Keywords: operational space control redundancy forward models inverse models compliance reinforcement leanring locally weighted learning] [PDF]

Peters, J.;Schaal, S. (2006). Reinforcement Learning for Parameterized Motor Primitives, Proceedings of the 2006 International Joint Conference on Neural Networks (IJCNN 2006).
[Keywords: motor primitives, reinforcement learning] [PDF]

Ting, J.;Mistry, M.;Nakanishi, J.;Peters, J.;Schaal, S. (2006). A Bayesian approach to nonlinear parameter identification for rigid body dynamics, in: Burgard, W.;Sukhatme, G. S.;Schaal, S. (eds.), Robotics: Science and Systems (RSS 2006), Cambridge, MA: MIT Press.
[Keywords: Bayesian regression linear models dimensionality reduction input noise rigid body dynamics parameter identification] [PDF]

Peters, J.;Schaal, S. (2006). Policy gradient methods for robotics, Proceedings of the IEEE International Conference on Intelligent Robotics Systems (IROS 2006).
[Keywords: policy gradient methods, reinforcement learning, robotics] [PDF]

Nakanishi, J.;Cory, R.;Mistry, M.;Peters, J.;Schaal, S. (2005). Comparative experiments on task space control with redundancy resolution, IEEE International Conference on Intelligent Robots and Systems (IROS 2005), pp.3901-3908.
[Keywords: manipulator dynamics redundant manipulators space optimization dynamical decoupling humanoid robots inverse kinematics motor coordination redundancy resolution robot dynamics seven-degree-of-freedom anthropomorphic robot arm task space control Dynamical d] [PDF]

Peters, J.;Vijayakumar, S.;Schaal, S. (2005). Natural Actor-Critic, in: Gama, J.;Camacho, R.;Brazdil, P.;Jorge, A.;Torgo, L. (eds.), Proceedings of the 16th European Conference on Machine Learning (ECML 2005), 3720, pp.280-291, Springer.
[Keywords: Reinforcement Learning, Policy Gradients, Natural Gradients] [PDF]

Peters, J.;Mistry, M.;Udwadia, F. E.;Schaal, S. (2005). A new methodology for robot control design, The 5th ASME International Conference on Multibody Systems, Nonlinear Dynamics, and Control (MSNDC 2005).
[Keywords: robot control, nonlinear control, gauss principle] [PDF]

Peters, J.;Mistry, M.;Udwadia, F. E.;Cory, R.;Nakanishi, J.;Schaal, S. (2005). A unifying framework for the control of robotics systems, IEEE International Conference on Intelligent Robots and Systems (IROS 2005), pp.1824-1831. [PDF]

Schaal, S.;Peters, J.;Nakanishi, J.;Ijspeert, A. (2004). Learning Movement Primitives, International Symposium on Robotics Research (ISRR2003), Springer.
[Keywords: movement primitives, supervised learning, reinforcment learning, locomotion, phase resetting, learning from demonstration] [PDF]

Peters, J.; Schaal, S. (2004). Learning Motor Primitives with Reinforcement Learning, Proceedings of the 11th Joint Symposium on Neural Computation.
[Keywords: natural policy gradients, motor primitives, natural actor-critic]

Mohajerian, P.;Peters, J.;Ijspeert, A.;Schaal, S. (2003). A unifying computational framework for optimization and dynamic systems approaches to motor control, Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003).
[Keywords: computational motor control, optimization, dynamic systems, formal modeling] [PDF]

Peters, J.;Vijayakumar, S.;Schaal, S. (2003). Reinforcement learning for humanoid robotics, IEEE-RAS International Conference on Humanoid Robots (Humanoids2003).
[Keywords: reinforcement learning, policy gradients, movement primitives, behaviors, dynamic systems, humanoid robotics] [PDF]

Peters, J.;Vijayakumar, S.;Schaal, S. (2003). Scaling reinforcement learning paradigms for motor learning, Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003).
[Keywords: Reinforcement learning, neurodynamic programming, actorcritic methods, policy gradient methods, natural policy gradient] [PDF]

Schaal, S.;Peters, J.;Nakanishi, J.;Ijspeert, A. (2003). Control, planning, learning, and imitation with dynamic movement primitives, Workshop on Bilateral Paradigms on Humans and Humanoids, IEEE International Conference on Intelligent Robots and Systems (IROS 2003).
[Keywords: movement primitives, supervised learning, reinforcment learning, locomotion, phase resetting, learning from demonstration] [PDF]

Burdet, E.; Tee, K.P.; Chew, C.M.; Peters, J.; Bt, V.L. (2001). Hybrid IDM/Impedance Learning in Human Movements, First International Symposium on Measurement, Analysis and Modeling of Human Functions Proceedings.
[Keywords: human motor control]

Peters, J; Riener, R (2000). A real-time model of the human knee for application in virtual orthopaedic trainer, Proceedings of the 10th International Conference on Biomedical Engineering Conference (ICBME).
[Keywords: Biomechanics, human motor control]


Page last modified on June 30, 2009, at 03:28 PM
Designed by J.Peters & N.Ohanyan. Powered by PmWiki.
This page is an unofficial page only helping to inform the reader of the RoLL's research. The Max-Planck Society is not responsible for the content.