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 Gaurav Sukhatme

Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning


Jun 29, 2021
K. R. Zentner, Ryan Julian, Ujjwal Puri, Yulun Zhang, Gaurav Sukhatme

* Accepted to Challenges of Real World Reinforcement Learning, Virtual Workshop at NeurIPS 2020 

  Access Paper or Ask Questions

Towards Exploiting Geometry and Time for FastOff-Distribution Adaptation in Multi-Task RobotLearning


Jun 24, 2021
K. R. Zentner, Ryan Julian, Ujjwal Puri, Yulun Zhang, Gaurav Sukhatme

* Accepted to Challenges of Real World Reinforcement Learning, Virtual Workshop at NeurIPS 2020 

  Access Paper or Ask Questions

Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning


Jun 23, 2020
Aleksei Petrenko, Zhehui Huang, Tushar Kumar, Gaurav Sukhatme, Vladlen Koltun

* Paper published in ICML2020. Visualizations of trained policies can be found at https://sites.google.com/view/sample-factory 

  Access Paper or Ask Questions

Encoding Physical Constraints in Differentiable Newton-Euler Algorithm


Feb 19, 2020
Giovanni Sutanto, Austin S. Wang, Yixin Lin, Mustafa Mukadam, Gaurav Sukhatme, Akshara Rai, Franziska Meier

* 10 pages (i.e. 8 pages of technical content and 2 pages of the Bibliography/References), submitted and currently under review for publication at the 2nd Learning for Dynamics and Control (L4DC) Conference, year 2020 

  Access Paper or Ask Questions

Meta-Learning via Learned Loss


Jun 12, 2019
Yevgen Chebotar, Artem Molchanov, Sarah Bechtle, Ludovic Righetti, Franziska Meier, Gaurav Sukhatme


  Access Paper or Ask Questions

Accelerating Goal-Directed Reinforcement Learning by Model Characterization


Jan 04, 2019
Shoubhik Debnath, Gaurav Sukhatme, Lantao Liu

* The paper was published in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 

  Access Paper or Ask Questions

Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times


Jan 04, 2019
Shoubhik Debnath, Lantao Liu, Gaurav Sukhatme

* The paper was published in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 

  Access Paper or Ask Questions

Reachability and Differential based Heuristics for Solving Markov Decision Processes


Jan 03, 2019
Shoubhik Debnath, Lantao Liu, Gaurav Sukhatme

* The paper was published in 2017 International Symposium on Robotics Research (ISRR) 

  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

Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena


Aug 09, 2014
Jie Chen, Kian Hsiang Low, Colin Keng-Yan Tan, Ali Oran, Patrick Jaillet, John Dolan, Gaurav Sukhatme

* Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012) 

  Access Paper or Ask Questions