Coline Devin

I am a PhD student in BAIR at UC Berkeley, advised by Professors Sergey Levine, Pieter Abbeel and Trevor Darrell. I graduated in Computer Science from Harvey Mudd College in May 2015, and I have previously interned at Google Deepmind and MILA. I am supported by the NSF GRFP.

CV  /  Google Scholar  /  GitHub


My research interests lie at the intersections of deep learning and robotics. As data is the main driver for deep learning, and robotic data tends to be sparse, my work has focused on transferring learned behaviors from simulation, other robots and tasks, and visual models.

Deep Object-Centric Representations for Generalizable Robot Learning
Coline Devin, Pieter Abbeel, Trevor Darrell, Sergey Levine
Accepted at ICRA 2018
arxiv / webpage / code

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
Abhishek Gupta*, Coline Devin*, YuXuan Liu, Pieter Abbeel, Sergey Levine
ICLR, 2017
webpage / video

Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer
Coline Devin*, Abhishek Gupta*, Trevor Darrell, Pieter Abbeel, Sergey Levine
ICRA, 2017
arxiv / webpage / video

Adapting deep visuomotor representations with weak pairwise constraints
Eric Tzeng*, Coline Devin*, Judy Hoffman, Chelsea Finn, Pieter Abbeel, Sergey Levine, Kate Saenko, Trevor Darrell
WAFR, 2016

Embedding word similarity with neural machine translation
Felix Hill, Kyunghyun Cho, Sebastien Jean, Coline Devin, Yoshua Bengio
ICLR workshop, 2015

Not all neural embeddings are born equal
Felix Hill, Kyunghyun Cho, Sebastien Jean, Coline Devin, Yoshua Bengio
Learning Semantics Workshop at NIPS, 2014

Website templatefrom Jon Barron.
Last updated August 2018.