Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Oct 26, 2020
Younggyo Seo, Kimin Lee, Ignasi Clavera, Thanard Kurutach, Jinwoo Shin, Pieter Abbeel

* Accepted in NeurIPS2020. First two authors contributed equally, website: https://sites.google.com/view/trajectory-mcl code: https://github.com/younggyoseo/trajectory_mcl 

  Access Paper or Ask Questions

LaND: Learning to Navigate from Disengagements

Oct 09, 2020
Gregory Kahn, Pieter Abbeel, Sergey Levine


  Access Paper or Ask Questions

Decoupling Representation Learning from Reinforcement Learning

Sep 30, 2020
Adam Stooke, Kimin Lee, Pieter Abbeel, Michael Laskin

* Improved related works and fixed code hyperlink 

  Access Paper or Ask Questions

Visual Imitation Made Easy

Aug 11, 2020
Sarah Young, Dhiraj Gandhi, Shubham Tulsiani, Abhinav Gupta, Pieter Abbeel, Lerrel Pinto


  Access Paper or Ask Questions

Hybrid Discriminative-Generative Training via Contrastive Learning

Aug 10, 2020
Hao Liu, Pieter Abbeel

* Code: https://github.com/lhao499/HDGE 

  Access Paper or Ask Questions

Robust Reinforcement Learning using Adversarial Populations

Aug 04, 2020
Eugene Vinitsky, Yuqing Du, Kanaad Parvate, Kathy Jang, Pieter Abbeel, Alexandre Bayen


  Access Paper or Ask Questions

Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

Aug 03, 2020
Xingyu Lu, Kimin Lee, Pieter Abbeel, Stas Tiomkin

* 16 pages 

  Access Paper or Ask Questions

Efficient Online Estimation of Empowerment for Reinforcement Learning

Jul 14, 2020
Ruihan Zhao, Pieter Abbeel, Stas Tiomkin


  Access Paper or Ask Questions

Variable Skipping for Autoregressive Range Density Estimation

Jul 10, 2020
Eric Liang, Zongheng Yang, Ion Stoica, Pieter Abbeel, Yan Duan, Xi Chen

* ICML 2020. Code released at: https://var-skip.github.io/ 

  Access Paper or Ask Questions

AvE: Assistance via Empowerment

Jul 09, 2020
Yuqing Du, Stas Tiomkin, Emre Kiciman, Daniel Polani, Pieter Abbeel, Anca Dragan

* Fix missing citation on page 4; edit acknowledgements 

  Access Paper or Ask Questions

Contrastive Code Representation Learning

Jul 09, 2020
Paras Jain, Ajay Jain, Tianjun Zhang, Pieter Abbeel, Joseph E. Gonzalez, Ion Stoica


  Access Paper or Ask Questions

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Jul 09, 2020
Kimin Lee, Michael Laskin, Aravind Srinivas, Pieter Abbeel


  Access Paper or Ask Questions

Self-Supervised Policy Adaptation during Deployment

Jul 08, 2020
Nicklas Hansen, Yu Sun, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang

* Project page: https://nicklashansen.github.io/PAD/ , Code: https://github.com/nicklashansen/policy-adaptation-during-deployment 

  Access Paper or Ask Questions

Responsive Safety in Reinforcement Learning by PID Lagrangian Methods

Jul 08, 2020
Adam Stooke, Joshua Achiam, Pieter Abbeel

* ICML 2020 

  Access Paper or Ask Questions

Locally Masked Convolution for Autoregressive Models

Jun 27, 2020
Ajay Jain, Pieter Abbeel, Deepak Pathak

* Published at Conference on Uncertainty in AI (UAI) 2020 

  Access Paper or Ask Questions

Denoising Diffusion Probabilistic Models

Jun 19, 2020
Jonathan Ho, Ajay Jain, Pieter Abbeel


  Access Paper or Ask Questions

Automatic Curriculum Learning through Value Disagreement

Jun 17, 2020
Yunzhi Zhang, Pieter Abbeel, Lerrel Pinto

* https://sites.google.com/berkeley.edu/vds/ 

  Access Paper or Ask Questions

Mutual Information Maximization for Robust Plannable Representations

May 16, 2020
Yiming Ding, Ignasi Clavera, Pieter Abbeel

* Accepted at NeurIPS 2019 Workshop on Robot Learning: Control and Interaction in the Real World 

  Access Paper or Ask Questions

Model-Augmented Actor-Critic: Backpropagating through Paths

May 16, 2020
Ignasi Clavera, Violet Fu, Pieter Abbeel

* Accepted paper at ICLR 2020 

  Access Paper or Ask Questions

Planning to Explore via Self-Supervised World Models

May 12, 2020
Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis, Pieter Abbeel, Danijar Hafner, Deepak Pathak

* Videos and code at https://ramanans1.github.io/plan2explore/ 

  Access Paper or Ask Questions

Reinforcement Learning with Augmented Data

May 11, 2020
Michael Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas

* First two authors contributed equally, website: https://mishalaskin.github.io/rad code: https://github.com/MishaLaskin/rad and https://github.com/pokaxpoka/rad_procgen 

  Access Paper or Ask Questions

Plan2Vec: Unsupervised Representation Learning by Latent Plans

May 07, 2020
Ge Yang, Amy Zhang, Ari S. Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra

* Proceedings of Machine Learning Research, the 2nd Annual Conference on Learning for Dynamics and Control (2020) Volume 120, 1-12 
* code available at https://geyang.github.io/plan2vec 

  Access Paper or Ask Questions