Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Jan Peters

High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning


Jun 07, 2021
Antoine Grosnit, Rasul Tutunov, Alexandre Max Maraval, Ryan-Rhys Griffiths, Alexander I. Cowen-Rivers, Lin Yang, Lin Zhu, Wenlong Lyu, Zhitang Chen, Jun Wang, Jan Peters, Haitham Bou-Ammar


  Access Paper or Ask Questions

Robust Value Iteration for Continuous Control Tasks


May 25, 2021
Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg

* Accepted Paper at Robotics: Science and Systems 

  Access Paper or Ask Questions

Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers


May 17, 2021
Daniel Tanneberg, Elmar Rueckert, Jan Peters

* Nature Machine Intelligence, Vol. 2, December 2020, 753-763 
* Nature Machine Intelligence 

  Access Paper or Ask Questions

Stochastic Control through Approximate Bayesian Input Inference


May 17, 2021
Joe Watson, Hany Abdulsamad, Rolf Findeisen, Jan Peters

* Submitted to Transactions on Automatic Control Special Issue: Learning and Control. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 

  Access Paper or Ask Questions

Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning


May 11, 2021
Julen Urain, Anqi Li, Puze Liu, Carlo D'Eramo, Jan Peters

* 8 pages, RSS 2021, Robotics: Science and Systems 2021 

  Access Paper or Ask Questions

Value Iteration in Continuous Actions, States and Time


May 10, 2021
Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg

* Accepted at International Conference on Machine Learning (ICML) 2021 

  Access Paper or Ask Questions

Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation


May 05, 2021
Niklas Funk, Charles Schaff, Rishabh Madan, Takuma Yoneda, Julen Urain De Jesus, Joe Watson, Ethan K. Gordon, Felix Widmaier, Stefan Bauer, Siddhartha S. Srinivasa, Tapomayukh Bhattacharjee, Matthew R. Walter, Jan Peters


  Access Paper or Ask Questions

Reinforcement Learning using Guided Observability


Apr 22, 2021
Stephan Weigand, Pascal Klink, Jan Peters, Joni Pajarinen


  Access Paper or Ask Questions

Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative-Entropy Trust Regions


Mar 29, 2021
Hany Abdulsamad, Tim Dorau, Boris Belousov, Jia-Jie Zhu, Jan Peters


  Access Paper or Ask Questions

SKID RAW: Skill Discovery from Raw Trajectories


Mar 26, 2021
Daniel Tanneberg, Kai Ploeger, Elmar Rueckert, Jan Peters

* IEEE Robotics and Automation Letters 

  Access Paper or Ask Questions

Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning


Mar 25, 2021
Andrew S. Morgan, Daljeet Nandha, Georgia Chalvatzaki, Carlo D'Eramo, Aaron M. Dollar, Jan Peters

* IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, 2021 

  Access Paper or Ask Questions

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk


Mar 10, 2021
Joe Watson, Jan Peters

* American Control Conference (ACC) 2021 

  Access Paper or Ask Questions

Extended Task and Motion Planning of Long-horizon Robot Manipulation


Mar 09, 2021
Tianyu Ren, Georgia Chalvatzaki, Jan Peters


  Access Paper or Ask Questions

Learning Human-like Hand Reaching for Human-Robot Handshaking


Feb 28, 2021
Vignesh Prasad, Ruth Stock-Homburg, Jan Peters

* Pre-print version. Accepted for Publication at ICRA'21 

  Access Paper or Ask Questions

A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning


Feb 25, 2021
Pascal Klink, Hany Abdulsamad, Boris Belousov, Carlo D'Eramo, Jan Peters, Joni Pajarinen


  Access Paper or Ask Questions

Human-Robot Handshaking: A Review


Feb 14, 2021
Vignesh Prasad, Ruth Stock-Homburg, Jan Peters

* Pre-print version. Accepted for publication in the International Journal of Social Robotics 

  Access Paper or Ask Questions

Structured Policy Representation: Imposing Stability in arbitrarily conditioned dynamic systems


Dec 11, 2020
Julen Urain, Davide Tateo, Tianyu Ren, Jan Peters

* Presented in NeurIPS 2020, 3rd Robot Learning Workshop. Stability, Few-Shot Learning, Deep Dynamic Systems 

  Access Paper or Ask Questions

Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop


Dec 07, 2020
Sebastian Höfer, Kostas Bekris, Ankur Handa, Juan Camilo Gamboa, Florian Golemo, Melissa Mozifian, Chris Atkeson, Dieter Fox, Ken Goldberg, John Leonard, C. Karen Liu, Jan Peters, Shuran Song, Peter Welinder, Martha White

* Summary of the "2nd Workshop on Closing the Reality Gap in Sim2Real Transfer for Robotics" held in conjunction with "Robotics: Science and System 2020". Website: https://sim2real.github.io/ 

  Access Paper or Ask Questions

Convex Optimization with an Interpolation-based Projection and its Application to Deep Learning


Nov 13, 2020
Riad Akrour, Asma Atamna, Jan Peters


  Access Paper or Ask Questions

A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning


Nov 10, 2020
Hany Abdulsamad, Peter Nickl, Pascal Klink, Jan Peters


  Access Paper or Ask Questions

Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning


Nov 03, 2020
Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters


  Access Paper or Ask Questions

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


Oct 31, 2020
Kai Ploeger, Michael Lutter, Jan Peters

* Published at Conference on Robot Learning (CoRL) 2020 

  Access Paper or Ask Questions

Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient


Oct 29, 2020
Samuele Tosatto, João Carvalho, Jan Peters

* arXiv admin note: substantial text overlap with arXiv:2001.02435 

  Access Paper or Ask Questions

Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills


Oct 26, 2020
Samuele Tosatto, Georgia Chalvatzaki, Jan Peters


  Access Paper or Ask Questions

ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows


Oct 25, 2020
Julen Urain, Michelle Ginesi, Davide Tateo, Jan Peters

* 7pages, 7 figures, IROS 2020 

  Access Paper or Ask Questions

A Differentiable Newton Euler Algorithm for Multi-body Model Learning


Oct 19, 2020
Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters

* ICML 2020 Workshop on Inductive Biases, Invariances and Generalization in Reinforcement Learning 

  Access Paper or Ask Questions

Differentiable Implicit Layers


Oct 14, 2020
Andreas Look, Simona Doneva, Melih Kandemir, Rainer Gemulla, Jan Peters


  Access Paper or Ask Questions

Active Inference or Control as Inference? A Unifying View


Oct 01, 2020
Joe Watson, Abraham Imohiosen, Jan Peters

* International Workshop on Active Inference 2020 (IWAI) 

  Access Paper or Ask Questions