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 Pieter Abbeel

Learning What To Do by Simulating the Past


Apr 08, 2021
David Lindner, Rohin Shah, Pieter Abbeel, Anca Dragan

* Published at ICLR 2021 

  Access Paper or Ask Questions

GEM: Group Enhanced Model for Learning Dynamical Control Systems


Apr 07, 2021
Philippe Hansen-Estruch, Wenling Shang, Lerrel Pinto, Pieter Abbeel, Stas Tiomkin

* 14 pages, 8 figures 

  Access Paper or Ask Questions

AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control


Apr 05, 2021
Xue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine, Angjoo Kanazawa


  Access Paper or Ask Questions

Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis


Apr 01, 2021
Ajay Jain, Matthew Tancik, Pieter Abbeel

* Project website: https://www.ajayj.com/dietnerf 

  Access Paper or Ask Questions

Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots


Mar 26, 2021
Zhongyu Li, Xuxin Cheng, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath

* To appear on 2021 International Conference on Robotics and Automation (ICRA 2021) 

  Access Paper or Ask Questions

Mutual Information State Intrinsic Control


Mar 15, 2021
Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu

* Published in International Conference on Learning Representations (ICLR 2021) as Spotlight (top 5%), Link: https://openreview.net/forum?id=OthEq8I5v1. arXiv admin note: text overlap with arXiv:2002.01963 

  Access Paper or Ask Questions

Behavior From the Void: Unsupervised Active Pre-Training


Mar 12, 2021
Hao Liu, Pieter Abbeel

* Corrected typos. Content unchanged 

  Access Paper or Ask Questions

Pretrained Transformers as Universal Computation Engines


Mar 09, 2021
Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch


  Access Paper or Ask Questions

Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings


Mar 04, 2021
Lili Chen, Kimin Lee, Aravind Srinivas, Pieter Abbeel


  Access Paper or Ask Questions

Task-Agnostic Morphology Evolution


Feb 25, 2021
Donald J. Hejna III, Pieter Abbeel, Lerrel Pinto

* ICLR 2021 

  Access Paper or Ask Questions

State Entropy Maximization with Random Encoders for Efficient Exploration


Feb 18, 2021
Younggyo Seo, Lili Chen, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

* First two authors contributed equally, website: https://sites.google.com/view/re3-rl 

  Access Paper or Ask Questions

Bottleneck Transformers for Visual Recognition


Jan 27, 2021
Aravind Srinivas, Tsung-Yi Lin, Niki Parmar, Jonathon Shlens, Pieter Abbeel, Ashish Vaswani

* Technical Report, 20 pages, 13 figures, 19 tables 

  Access Paper or Ask Questions

Reinforcement Learning with Latent Flow


Jan 06, 2021
Wenling Shang, Xiaofei Wang, Aravind Srinivas, Aravind Rajeswaran, Yang Gao, Pieter Abbeel, Michael Laskin


  Access Paper or Ask Questions

Reset-Free Lifelong Learning with Skill-Space Planning


Jan 01, 2021
Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch

* Website link: https://sites.google.com/berkeley.edu/reset-free-lifelong-learning 

  Access Paper or Ask Questions

A Framework for Efficient Robotic Manipulation


Dec 14, 2020
Albert Zhan, Philip Zhao, Lerrel Pinto, Pieter Abbeel, Michael Laskin


  Access Paper or Ask Questions

Parallel Training of Deep Networks with Local Updates


Dec 07, 2020
Michael Laskin, Luke Metz, Seth Nabarrao, Mark Saroufim, Badreddine Noune, Carlo Luschi, Jascha Sohl-Dickstein, Pieter Abbeel

* First two authors - Michael Laskin and Luke Metz - contributed equally. Order was determined by a coin flip 

  Access Paper or Ask Questions

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