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 Garrett Thomas

Model-based Adversarial Meta-Reinforcement Learning

Jun 16, 2020
Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma

* Code at 

  Access Paper or Ask Questions

MOPO: Model-based Offline Policy Optimization

May 27, 2020
Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma

* First two authors contributed equally. Last two authors advised equally 

  Access Paper or Ask Questions

A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning

Jul 15, 2019
Nicholas C. Landolfi, Garrett Thomas, Tengyu Ma

* 13 pages, 3 figures 

  Access Paper or Ask Questions

Learning Robotic Assembly from CAD

Jul 24, 2018
Garrett Thomas, Melissa Chien, Aviv Tamar, Juan Aparicio Ojea, Pieter Abbeel

* In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, May 2018 

  Access Paper or Ask Questions

Learning from the Hindsight Plan -- Episodic MPC Improvement

Mar 20, 2017
Aviv Tamar, Garrett Thomas, Tianhao Zhang, Sergey Levine, Pieter Abbeel

* Additional experiments for neural network generalization and for varying the planning horizon. Paper accepted to ICRA 2017 

  Access Paper or Ask Questions

Value Iteration Networks

Mar 20, 2017
Aviv Tamar, Yi Wu, Garrett Thomas, Sergey Levine, Pieter Abbeel

* Advances in Neural Information Processing Systems 29 pages 2154--2162, 2016 
* Fixed missing table values 

  Access Paper or Ask Questions