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 Michael Neunert

"What, not how": Solving an under-actuated insertion task from scratch


Oct 30, 2020
Giulia Vezzani, Michael Neunert, Markus Wulfmeier, Rae Jeong, Thomas Lampe, Noah Siegel, Roland Hafner, Abbas Abdolmaleki, Martin Riedmiller, Francesco Nori


  Access Paper or Ask Questions

Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion


Aug 06, 2020
Roland Hafner, Tim Hertweck, Philipp Klöppner, Michael Bloesch, Michael Neunert, Markus Wulfmeier, Saran Tunyasuvunakool, Nicolas Heess, Martin Riedmiller


  Access Paper or Ask Questions

Data-efficient Hindsight Off-policy Option Learning


Jul 30, 2020
Markus Wulfmeier, Dushyant Rao, Roland Hafner, Thomas Lampe, Abbas Abdolmaleki, Tim Hertweck, Michael Neunert, Dhruva Tirumala, Noah Siegel, Nicolas Heess, Martin Riedmiller


  Access Paper or Ask Questions

A Distributional View on Multi-Objective Policy Optimization


May 15, 2020
Abbas Abdolmaleki, Sandy H. Huang, Leonard Hasenclever, Michael Neunert, H. Francis Song, Martina Zambelli, Murilo F. Martins, Nicolas Heess, Raia Hadsell, Martin Riedmiller


  Access Paper or Ask Questions

Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning


Feb 23, 2020
Noah Y. Siegel, Jost Tobias Springenberg, Felix Berkenkamp, Abbas Abdolmaleki, Michael Neunert, Thomas Lampe, Roland Hafner, Nicolas Heess, Martin Riedmiller

* To appear in ICLR 2020 

  Access Paper or Ask Questions

Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics


Jan 02, 2020
Michael Neunert, Abbas Abdolmaleki, Markus Wulfmeier, Thomas Lampe, Jost Tobias Springenberg, Roland Hafner, Francesco Romano, Jonas Buchli, Nicolas Heess, Martin Riedmiller

* Presented at the 3rd Conference on Robot Learning (CoRL 2019), Osaka, Japan. Video: https://youtu.be/eUqQDLQXb7I 

  Access Paper or Ask Questions

Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models


Oct 09, 2019
Arunkumar Byravan, Jost Tobias Springenberg, Abbas Abdolmaleki, Roland Hafner, Michael Neunert, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

* To appear at the 3rd annual Conference on Robot Learning, Osaka, Japan (CoRL 2019). 24 pages including appendix (main paper - 8 pages) 

  Access Paper or Ask Questions

Regularized Hierarchical Policies for Compositional Transfer in Robotics


Jun 27, 2019
Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg, Michael Neunert, Tim Hertweck, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

* Preprint. Under review. Addressed typos 

  Access Paper or Ask Questions

Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup


Feb 18, 2019
Devin Schwab, Tobias Springenberg, Murilo F. Martins, Thomas Lampe, Michael Neunert, Abbas Abdolmaleki, Tim Hertweck, Roland Hafner, Francesco Nori, Martin Riedmiller

* Videos can be found at https://sites.google.com/view/rss-2019-sawyer-bic/ 

  Access Paper or Ask Questions

Value constrained model-free continuous control


Feb 12, 2019
Steven Bohez, Abbas Abdolmaleki, Michael Neunert, Jonas Buchli, Nicolas Heess, Raia Hadsell


  Access Paper or Ask Questions

The Control Toolbox - An Open-Source C++ Library for Robotics, Optimal and Model Predictive Control


Mar 26, 2018
Markus Giftthaler, Michael Neunert, Markus StÀuble, Jonas Buchli


  Access Paper or Ask Questions

Learning by Playing - Solving Sparse Reward Tasks from Scratch


Feb 28, 2018
Martin Riedmiller, Roland Hafner, Thomas Lampe, Michael Neunert, Jonas Degrave, Tom Van de Wiele, Volodymyr Mnih, Nicolas Heess, Jost Tobias Springenberg

* A video of the rich set of learned behaviours can be found at https://youtu.be/mPKyvocNe_M 

  Access Paper or Ask Questions

Automatic Differentiation of Rigid Body Dynamics for Optimal Control and Estimation


Jan 16, 2018
Markus Giftthaler, Michael Neunert, Markus StÀuble, Marco Frigerio, Claudio Semini, Jonas Buchli

* Advanced Robotics, November 2017, Taylor and Francis 

  Access Paper or Ask Questions

A Family of Iterative Gauss-Newton Shooting Methods for Nonlinear Optimal Control


Dec 11, 2017
Markus Giftthaler, Michael Neunert, Markus StÀuble, Jonas Buchli, Moritz Diehl

* 8 pages 

  Access Paper or Ask Questions

Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds


Dec 07, 2017
Michael Neunert, Markus StÀuble, Markus Giftthaler, Carmine D. Bellicoso, Jan Carius, Christian Gehring, Marco Hutter, Jonas Buchli

* Submitted to "Robotics and Automation: Letters" / "International Conference on Robotics and Automation 2018" 

  Access Paper or Ask Questions

Fast Trajectory Optimization for Legged Robots using Vertex-based ZMP Constraints


May 27, 2017
Alexander W Winkler, Farbod Farshidian, Diego Pardo, Michael Neunert, Jonas Buchli

* currently under review for IEEE RA-L 

  Access Paper or Ask Questions

An Efficient Optimal Planning and Control Framework For Quadrupedal Locomotion


Mar 04, 2017
Farbod Farshidian, Michael Neunert, Alexander W. Winkler, Gonzalo Rey, Jonas Buchli

* 8 Pages 

  Access Paper or Ask Questions

Trajectory Optimization Through Contacts and Automatic Gait Discovery for Quadrupeds


Jul 15, 2016
Michael Neunert, Farbod Farshidian, Alexander W. Winkler, Jonas Buchli

* Video: https://youtu.be/sILuqJBsyKs 

  Access Paper or Ask Questions

An Open Source, Fiducial Based, Visual-Inertial Motion Capture System


Jun 13, 2016
Michael Neunert, Michael Bloesch, Jonas Buchli

* To appear in The International Conference on Information Fusion (FUSION) 2016 

  Access Paper or Ask Questions

Evaluating direct transcription and nonlinear optimization methods for robot motion planning


Jan 29, 2016
Diego Pardo, Lukas Möller, Michael Neunert, Alexander W. Winkler, Jonas Buchli


  Access Paper or Ask Questions

Projection based whole body motion planning for legged robots


Oct 06, 2015
Diego Pardo, Michael Neunert, Alexander W. Winkler, Jonas Buchli


  Access Paper or Ask Questions