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 Benjamin Eysenbach

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks


Oct 22, 2021
Tianjun Zhang, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Joseph E. Gonzalez


  Access Paper or Ask Questions

Recurrent Model-Free RL is a Strong Baseline for Many POMDPs


Oct 11, 2021
Tianwei Ni, Benjamin Eysenbach, Ruslan Salakhutdinov


  Access Paper or Ask Questions

Mismatched No More: Joint Model-Policy Optimization for Model-Based RL


Oct 06, 2021
Benjamin Eysenbach, Alexander Khazatsky, Sergey Levine, Ruslan Salakhutdinov


  Access Paper or Ask Questions

The Information Geometry of Unsupervised Reinforcement Learning


Oct 06, 2021
Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine


  Access Paper or Ask Questions

Robust Predictable Control


Sep 07, 2021
Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

* Project site with videos and code: https://ben-eysenbach.github.io/rpc 

  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

RECON: Rapid Exploration for Open-World Navigation with Latent Goal Models


Apr 14, 2021
Dhruv Shah, Benjamin Eysenbach, Nicholas Rhinehart, Sergey Levine


  Access Paper or Ask Questions

Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification


Mar 23, 2021
Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov

* Website with videos and code: https://ben-eysenbach.github.io/rce 

  Access Paper or Ask Questions

Maximum Entropy RL (Provably) Solves Some Robust RL Problems


Mar 10, 2021
Benjamin Eysenbach, Sergey Levine

* Blog post and videos: https://bair.berkeley.edu/blog/2021/03/10/maxent-robust-rl/. arXiv admin note: text overlap with arXiv:1910.01913 

  Access Paper or Ask Questions

Model-Based Visual Planning with Self-Supervised Functional Distances


Dec 30, 2020
Stephen Tian, Suraj Nair, Frederik Ebert, Sudeep Dasari, Benjamin Eysenbach, Chelsea Finn, Sergey Levine


  Access Paper or Ask Questions

ViNG: Learning Open-World Navigation with Visual Goals


Dec 17, 2020
Dhruv Shah, Benjamin Eysenbach, Gregory Kahn, Nicholas Rhinehart, Sergey Levine


  Access Paper or Ask Questions

C-Learning: Learning to Achieve Goals via Recursive Classification


Nov 17, 2020
Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

* Project website: https://ben-eysenbach.github.io/c_learning/ 

  Access Paper or Ask Questions

f-IRL: Inverse Reinforcement Learning via State Marginal Matching


Nov 09, 2020
Tianwei Ni, Harshit Sikchi, Yufei Wang, Tejus Gupta, Lisa Lee, Benjamin Eysenbach

* The first four authors have equal contribution (orders determined by dice rolling), and the last two authors have equal advising. The paper is accepted by Conference on Robot Learning (CoRL) 2020. Project videos and code link are available at https://sites.google.com/view/f-irl/home 

  Access Paper or Ask Questions

Learning to be Safe: Deep RL with a Safety Critic


Oct 27, 2020
Krishnan Srinivasan, Benjamin Eysenbach, Sehoon Ha, Jie Tan, Chelsea Finn

* In submission, 16 pages (including appendix) 

  Access Paper or Ask Questions

Interactive Visualization for Debugging RL


Aug 18, 2020
Shuby Deshpande, Benjamin Eysenbach, Jeff Schneider

* Builds on preliminary work presented at ICML 2020 (WHI) arXiv:2007.05577. An interactive demo of the system can be at https://tinyurl.com/y5gv5t4m 

  Access Paper or Ask Questions

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers


Jun 24, 2020
Benjamin Eysenbach, Swapnil Asawa, Shreyas Chaudhari, Ruslan Salakhutdinov, Sergey Levine


  Access Paper or Ask Questions

Weakly-Supervised Reinforcement Learning for Controllable Behavior


Apr 06, 2020
Lisa Lee, Benjamin Eysenbach, Ruslan Salakhutdinov, Shixiang, Gu, Chelsea Finn


  Access Paper or Ask Questions

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement


Feb 25, 2020
Benjamin Eysenbach, Xinyang Geng, Sergey Levine, Ruslan Salakhutdinov


  Access Paper or Ask Questions

Learning To Reach Goals Without Reinforcement Learning


Dec 13, 2019
Dibya Ghosh, Abhishek Gupta, Justin Fu, Ashwin Reddy, Coline Devin, Benjamin Eysenbach, Sergey Levine

* First two authors contributed equally 

  Access Paper or Ask Questions

If MaxEnt RL is the Answer, What is the Question?


Oct 04, 2019
Benjamin Eysenbach, Sergey Levine


  Access Paper or Ask Questions

Efficient Exploration via State Marginal Matching


Jun 12, 2019
Lisa Lee, Benjamin Eysenbach, Emilio Parisotto, Eric Xing, Sergey Levine, Ruslan Salakhutdinov

* Videos and code: https://sites.google.com/view/state-marginal-matching 

  Access Paper or Ask Questions

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning


Jun 12, 2019
Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

* Run our algorithm in your browser: http://bit.ly/rl_search 

  Access Paper or Ask Questions

Diversity is All You Need: Learning Skills without a Reward Function


Oct 09, 2018
Benjamin Eysenbach, Abhishek Gupta, Julian Ibarz, Sergey Levine

* Videos and code for our experiments are available at: https://sites.google.com/view/diayn 

  Access Paper or Ask Questions

Unsupervised Meta-Learning for Reinforcement Learning


Jun 12, 2018
Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine


  Access Paper or Ask Questions

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings


Jun 07, 2018
John D. Co-Reyes, YuXuan Liu, Abhishek Gupta, Benjamin Eysenbach, Pieter Abbeel, Sergey Levine

* Accepted at ICML 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