activity
20172022
most citedLearning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning

107 citations · 128 across the 4 of their papers we have counts for

collaborators
Showing cs.ROShow all

5 papers · 1 filter

cs.RO20221 cited

How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation

Alex X. Lee, Coline Devin, Jost Tobias Springenberg +4

Reinforcement learning (RL) has been shown to be effective at learning control from experience. However, RL typically requires a large amount of online interaction with the environ…

cs.RO202116 cited

Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes

Alex X. Lee, Coline Devin, Yuxiang Zhou +18

We study the problem of robotic stacking with objects of complex geometry. We propose a challenging and diverse set of such objects that was carefully designed to require strategie…

cs.RO20204 cited

Self-Supervised Goal-Conditioned Pick and Place

Coline Devin, Payam Rowghanian, Chris Vigorito +2

Robots have the capability to collect large amounts of data autonomously by interacting with objects in the world. However, it is often not obvious \emph{how} to learning from auto…

cs.RO2018

Grasp2Vec: Learning Object Representations from Self-Supervised Grasping

Eric Jang, Coline Devin, Vincent Vanhoucke +1

Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representa…

cs.RO2017

Deep Object-Centric Representations for Generalizable Robot Learning

Coline Devin, Pieter Abbeel, Trevor Darrell +1

Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a met…