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 Coline Devin

Fully Autonomous Real-World Reinforcement Learning for Mobile Manipulation


Aug 03, 2021
Charles Sun, Jędrzej Orbik, Coline Devin, Brian Yang, Abhishek Gupta, Glen Berseth, Sergey Levine

* 16 pages 

  Access Paper or Ask Questions

ReLMM: Practical RL for Learning Mobile Manipulation Skills Using Only Onboard Sensors


Jul 28, 2021
Charles Sun, Jędrzej Orbik, Coline Devin, Brian Yang, Abhishek Gupta, Glen Berseth, Sergey Levine

* 17 pages 

  Access Paper or Ask Questions

Modularity Improves Out-of-Domain Instruction Following


Oct 24, 2020
Rodolfo Corona, Daniel Fried, Coline Devin, Dan Klein, Trevor Darrell


  Access Paper or Ask Questions

Self-Supervised Goal-Conditioned Pick and Place


Aug 26, 2020
Coline Devin, Payam Rowghanian, Chris Vigorito, Will Richards, Khashayar Rohanimanesh

* In RSS 2020 Visual Learning and Reasoning for Robotic Manipulation Workshop 

  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

SMiRL: Surprise Minimizing RL in Dynamic Environments


Dec 11, 2019
Glen Berseth, Daniel Geng, Coline Devin, Chelsea Finn, Dinesh Jayaraman, Sergey Levine

* PrePrint 

  Access Paper or Ask Questions

Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control


Oct 30, 2019
Coline Devin, Daniel Geng, Pieter Abbeel, Trevor Darrell, Sergey Levine

* In NeurIPS 2019 

  Access Paper or Ask Questions

Monocular Plan View Networks for Autonomous Driving


May 16, 2019
Dequan Wang, Coline Devin, Qi-Zhi Cai, Philipp Krähenbühl, Trevor Darrell

* 8 pages, 9 figures 

  Access Paper or Ask Questions

Deep Object-Centric Policies for Autonomous Driving


Mar 01, 2019
Dequan Wang, Coline Devin, Qi-Zhi Cai, Fisher Yu, Trevor Darrell

* Accepted at ICRA 2019 

  Access Paper or Ask Questions

Grasp2Vec: Learning Object Representations from Self-Supervised Grasping


Nov 19, 2018
Eric Jang, Coline Devin, Vincent Vanhoucke, Sergey Levine

* Proceedings of The 2nd Conference on Robot Learning, in PMLR 87:99-112 (2018) 
* CoRL 2018. Eric Jang and Coline Devin contributed equally to this work 

  Access Paper or Ask Questions

Deep Object Centric Policies for Autonomous Driving


Nov 13, 2018
Dequan Wang, Coline Devin, Qi-Zhi Cai, Fisher Yu, Trevor Darrell


  Access Paper or Ask Questions

Deep Object-Centric Representations for Generalizable Robot Learning


Sep 26, 2017
Coline Devin, Pieter Abbeel, Trevor Darrell, Sergey Levine


  Access Paper or Ask Questions

Adapting Deep Visuomotor Representations with Weak Pairwise Constraints


May 25, 2017
Eric Tzeng, Coline Devin, Judy Hoffman, Chelsea Finn, Pieter Abbeel, Sergey Levine, Kate Saenko, Trevor Darrell


  Access Paper or Ask Questions

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning


Mar 08, 2017
Abhishek Gupta, Coline Devin, YuXuan Liu, Pieter Abbeel, Sergey Levine

* Published as a conference paper at ICLR 2017 

  Access Paper or Ask Questions

Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer


Sep 22, 2016
Coline Devin, Abhishek Gupta, Trevor Darrell, Pieter Abbeel, Sergey Levine

* Under review at the International Conference on Robotics and Automation (ICRA) 2017 

  Access Paper or Ask Questions

Embedding Word Similarity with Neural Machine Translation


Apr 03, 2015
Felix Hill, Kyunghyun Cho, Sebastien Jean, Coline Devin, Yoshua Bengio

* arXiv admin note: text overlap with arXiv:1410.0718 

  Access Paper or Ask Questions

Not All Neural Embeddings are Born Equal


Nov 13, 2014
Felix Hill, KyungHyun Cho, Sebastien Jean, Coline Devin, Yoshua Bengio

* 4 pages plus 1 page of references 

  Access Paper or Ask Questions