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 Shixiang Gu

Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization


Jun 23, 2020
Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo, Ofir Nachum, Shixiang Gu


  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

A Divergence Minimization Perspective on Imitation Learning Methods


Nov 06, 2019
Seyed Kamyar Seyed Ghasemipour, Richard Zemel, Shixiang Gu

* Published at Conference on Robot Learning (CoRL) 2019. For datasets and reproducing results please refer to https://github.com/KamyarGh/rl_swiss/blob/master/reproducing/fmax_paper.md 

  Access Paper or Ask Questions

Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?


Sep 23, 2019
Ofir Nachum, Haoran Tang, Xingyu Lu, Shixiang Gu, Honglak Lee, Sergey Levine


  Access Paper or Ask Questions

Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real


Aug 13, 2019
Ofir Nachum, Michael Ahn, Hugo Ponte, Shixiang Gu, Vikash Kumar


  Access Paper or Ask Questions

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog


Jul 08, 2019
Natasha Jaques, Asma Ghandeharioun, Judy Hanwen Shen, Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, Rosalind Picard


  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

Language as an Abstraction for Hierarchical Deep Reinforcement Learning


Jun 18, 2019
Yiding Jiang, Shixiang Gu, Kevin Murphy, Chelsea Finn

* 20 pages, 21 figures 

  Access Paper or Ask Questions

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives


Oct 09, 2018
George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison


  Access Paper or Ask Questions

Data-Efficient Hierarchical Reinforcement Learning


Oct 05, 2018
Ofir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine

* NIPS 2018 

  Access Paper or Ask Questions

Near-Optimal Representation Learning for Hierarchical Reinforcement Learning


Oct 02, 2018
Ofir Nachum, Shixiang Gu, Honglak Lee, Sergey Levine


  Access Paper or Ask Questions

The Mirage of Action-Dependent Baselines in Reinforcement Learning


Apr 06, 2018
George Tucker, Surya Bhupatiraju, Shixiang Gu, Richard E. Turner, Zoubin Ghahramani, Sergey Levine

* Updated to address comments from ICLR workshop reviewers 

  Access Paper or Ask Questions

Temporal Difference Models: Model-Free Deep RL for Model-Based Control


Feb 25, 2018
Vitchyr Pong, Shixiang Gu, Murtaza Dalal, Sergey Levine

* To appear in ICLR 2018 

  Access Paper or Ask Questions

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning


Nov 18, 2017
Benjamin Eysenbach, Shixiang Gu, Julian Ibarz, Sergey Levine

* Videos of our experiments are available at: https://sites.google.com/site/mlleavenotrace/ 

  Access Paper or Ask Questions

Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control


Oct 16, 2017
Natasha Jaques, Shixiang Gu, Dzmitry Bahdanau, José Miguel Hernández-Lobato, Richard E. Turner, Douglas Eck

* Add supplementary material 

  Access Paper or Ask Questions

Categorical Reparameterization with Gumbel-Softmax


Aug 05, 2017
Eric Jang, Shixiang Gu, Ben Poole


  Access Paper or Ask Questions

Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning


Jun 01, 2017
Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Bernhard Schölkopf, Sergey Levine


  Access Paper or Ask Questions

Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic


Feb 27, 2017
Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine

* Conference Paper at the International Conference on Learning Representations (ICLR) 2017 

  Access Paper or Ask Questions

Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates


Nov 23, 2016
Shixiang Gu, Ethan Holly, Timothy Lillicrap, Sergey Levine


  Access Paper or Ask Questions

Continuous Deep Q-Learning with Model-based Acceleration


Mar 02, 2016
Shixiang Gu, Timothy Lillicrap, Ilya Sutskever, Sergey Levine


  Access Paper or Ask Questions

MuProp: Unbiased Backpropagation for Stochastic Neural Networks


Feb 25, 2016
Shixiang Gu, Sergey Levine, Ilya Sutskever, Andriy Mnih

* Published as a conference paper at ICLR 2016 

  Access Paper or Ask Questions

Neural Adaptive Sequential Monte Carlo


Nov 16, 2015
Shixiang Gu, Zoubin Ghahramani, Richard E. Turner


  Access Paper or Ask Questions

Towards Deep Neural Network Architectures Robust to Adversarial Examples


Apr 09, 2015
Shixiang Gu, Luca Rigazio


  Access Paper or Ask Questions