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 David Hoeller

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning


Sep 24, 2021
Nikita Rudin, David Hoeller, Philipp Reist, Marco Hutter

* CoRL 2021 

  Access Paper or Ask Questions

Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning


Aug 25, 2021
Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo, Michelle Lu, Kier Storey, Miles Macklin, David Hoeller, Nikita Rudin, Arthur Allshire, Ankur Handa, Gavriel State

* tech report on isaac-gym 

  Access Paper or Ask Questions

Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation


Mar 18, 2021
Mayank Mittal, David Hoeller, Farbod Farshidian, Marco Hutter, Animesh Garg


  Access Paper or Ask Questions

Learning a State Representation and Navigation in Cluttered and Dynamic Environments


Mar 07, 2021
David Hoeller, Lorenz Wellhausen, Farbod Farshidian, Marco Hutter

* IEEE Robotics and Automation Letters 2021 
* 8 pages, 8 figures, 2 tables 

  Access Paper or Ask Questions

Joint Space Control via Deep Reinforcement Learning


Nov 12, 2020
Visak Kumar, David Hoeller, Balakumar Sundaralingam, Jonathan Tremblay, Stan Birchfield

* Submitted to ICRA 2021 

  Access Paper or Ask Questions

Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion


Oct 05, 2020
Xingye Da, Zhaoming Xie, David Hoeller, Byron Boots, Animashree Anandkumar, Yuke Zhu, Buck Babich, Animesh Garg

* supplementary video: https://youtu.be/JJOmFZKpYTo 

  Access Paper or Ask Questions

Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robot


Mar 06, 2020
Napat Karnchanachari, Miguel I. Valls, David Hoeller, Marco Hutter

* 14 pages, 6 figures, submitted to L4DC 2020 

  Access Paper or Ask Questions

Deep Value Model Predictive Control


Oct 08, 2019
Farbod Farshidian, David Hoeller, Marco Hutter

* Accepted for publication in the Conference on Robotic Learning (CoRL) 2019, Osaka. 10 pages (+5 supplementary) 

  Access Paper or Ask Questions