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 Karol Hausman

Karol Hausman

Google Brain

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning


Sep 16, 2021
Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn


  Access Paper or Ask Questions

Persistent Reinforcement Learning via Subgoal Curricula


Jul 27, 2021
Archit Sharma, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn


  Access Paper or Ask Questions

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills


Apr 28, 2021
Yevgen Chebotar, Karol Hausman, Yao Lu, Ted Xiao, Dmitry Kalashnikov, Jake Varley, Alex Irpan, Benjamin Eysenbach, Ryan Julian, Chelsea Finn, Sergey Levine


  Access Paper or Ask Questions

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale


Apr 27, 2021
Dmitry Kalashnikov, Jacob Varley, Yevgen Chebotar, Benjamin Swanson, Rico Jonschkowski, Chelsea Finn, Sergey Levine, Karol Hausman


  Access Paper or Ask Questions

A Geometric Perspective on Self-Supervised Policy Adaptation


Nov 14, 2020
Cristian Bodnar, Karol Hausman, Gabriel Dulac-Arnold, Rico Jonschkowski

* Contains 17 pages, 18 figures 

  Access Paper or Ask Questions

Confidence-rich grid mapping


Jun 29, 2020
Ali-akbar Agha-mohammadi, Eric Heiden, Karol Hausman, Gaurav S. Sukhatme

* The International Journal of Robotics Research, 38(12-13), 1352-1374 (2019) 
* Published at International Journal of Robotics Research (IJRR) 2019 (https://journals.sagepub.com/doi/10.1177/0278364919839762

  Access Paper or Ask Questions

Modeling Long-horizon Tasks as Sequential Interaction Landscapes


Jun 08, 2020
Sören Pirk, Karol Hausman, Alexander Toshev, Mohi Khansari

* More details available at: http://www.pirk.io 

  Access Paper or Ask Questions

Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning


Apr 27, 2020
Archit Sharma, Michael Ahn, Sergey Levine, Vikash Kumar, Karol Hausman, Shixiang Gu


  Access Paper or Ask Questions

Thinking While Moving: Deep Reinforcement Learning with Concurrent Control


Apr 25, 2020
Ted Xiao, Eric Jang, Dmitry Kalashnikov, Sergey Levine, Julian Ibarz, Karol Hausman, Alexander Herzog

* Published as a conference paper at ICLR 2020 

  Access Paper or Ask Questions

Efficient Adaptation for End-to-End Vision-Based Robotic Manipulation


Apr 21, 2020
Ryan Julian, Benjamin Swanson, Gaurav S. Sukhatme, Sergey Levine, Chelsea Finn, Karol Hausman

* 8.5 pages, 9 figures. See video overview and experiments at https://youtu.be/pPDVewcSpdc and project website at https://ryanjulian.me/continual-fine-tuning 

  Access Paper or Ask Questions

Gradient Surgery for Multi-Task Learning


Jan 19, 2020
Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn


  Access Paper or Ask Questions

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning


Oct 25, 2019
Abhishek Gupta, Vikash Kumar, Corey Lynch, Sergey Levine, Karol Hausman

* Published at CoRL 2019 

  Access Paper or Ask Questions

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning


Oct 24, 2019
Tianhe Yu, Deirdre Quillen, Zhanpeng He, Ryan Julian, Karol Hausman, Chelsea Finn, Sergey Levine

* CoRL 2019. Videos are here: meta-world.github.io and open-sourced codes are available at: https://github.com/rlworkgroup/metaworld 

  Access Paper or Ask Questions

Quantile QT-Opt for Risk-Aware Vision-Based Robotic Grasping


Oct 01, 2019
Cristian Bodnar, Adrian Li, Karol Hausman, Peter Pastor, Mrinal Kalakrishnan

* Under review at ICRA 2020 

  Access Paper or Ask Questions

Dynamics-Aware Unsupervised Discovery of Skills


Jul 02, 2019
Archit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar, Karol Hausman


  Access Paper or Ask Questions

Training an Interactive Helper


Jul 02, 2019
Mark Woodward, Chelsea Finn, Karol Hausman

* The paper "Learning to Interactively Learn and Assist" (LILA), at arXiv:1906.10187, supersedes this paper. This preliminary workshop paper appeared in the Emergent Communication Workshop and Workshop on Learning by Instruction at NeurIPS 2018 

  Access Paper or Ask Questions

Learning to Interactively Learn and Assist


Jul 01, 2019
Mark Woodward, Chelsea Finn, Karol Hausman

* Video overview at https://youtu.be/8yBvDBuAPrw, paper website with videos and interactive game at http://interactive-learning.github.io/ 

  Access Paper or Ask Questions

Scaling simulation-to-real transfer by learning composable robot skills


Nov 13, 2018
Ryan Julian, Eric Heiden, Zhanpeng He, Hejia Zhang, Stefan Schaal, Joseph J. Lim, Gaurav Sukhatme, Karol Hausman

* Presented at ISER 2018. See https://www.youtube.com/watch?v=Syr2RQTHqTs for supplemental video 

  Access Paper or Ask Questions

Zero-Shot Skill Composition and Simulation-to-Real Transfer by Learning Task Representations


Nov 13, 2018
Zhanpeng He, Ryan Julian, Eric Heiden, Hejia Zhang, Stefan Schaal, Joseph J. Lim, Gaurav Sukhatme, Karol Hausman

* Submitted to ICRA 2019. See https://youtu.be/te4JWe7LPKw for supplemental video 

  Access Paper or Ask Questions

Region Growing Curriculum Generation for Reinforcement Learning


Jul 04, 2018
Artem Molchanov, Karol Hausman, Stan Birchfield, Gaurav Sukhatme


  Access Paper or Ask Questions

Interactive Perception: Leveraging Action in Perception and Perception in Action


Dec 06, 2017
Jeannette Bohg, Karol Hausman, Bharath Sankaran, Oliver Brock, Danica Kragic, Stefan Schaal, Gaurav Sukhatme

* IEEE Transactions on Robotics 33 (2017) 1273-1291 
* Equal contribution by first three authors 

  Access Paper or Ask Questions

Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets


Nov 23, 2017
Karol Hausman, Yevgen Chebotar, Stefan Schaal, Gaurav Sukhatme, Joseph Lim

* Paper accepted to NIPS 2017 

  Access Paper or Ask Questions

Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning


Jun 18, 2017
Yevgen Chebotar, Karol Hausman, Marvin Zhang, Gaurav Sukhatme, Stefan Schaal, Sergey Levine

* Paper accepted to the International Conference on Machine Learning (ICML) 2017 

  Access Paper or Ask Questions

Observability-Aware Trajectory Optimization for Self-Calibration with Application to UAVs


Apr 27, 2016
Karol Hausman, James Preiss, Gaurav Sukhatme, Stephan Weiss


  Access Paper or Ask Questions