activity
20182022
most citedUnsupervised Curricula for Visual Meta-Reinforcement Learning

26 citations · 53 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV2022

Discovering Objects that Can Move

Zhipeng Bao, Pavel Tokmakov, Allan Jabri +3

This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, text…

cs.CV2020

Space-Time Correspondence as a Contrastive Random Walk

Allan Jabri, Andrew Owens, Alexei A. Efros

This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a spa…

cs.RO201921 cited

Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning

Richard Li, Allan Jabri, Trevor Darrell +1

Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require…

cs.AI201926 cited

Unsupervised Curricula for Visual Meta-Reinforcement Learning

Allan Jabri, Kyle Hsu, Ben Eysenbach +3

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. Howe…

cs.CV20196 cited

Learning Correspondence from the Cycle-Consistency of Time

Xiaolong Wang, Allan Jabri, Alexei A. Efros

We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for lear…

cs.LG2018

Universal Planning Networks

Aravind Srinivas, Allan Jabri, Pieter Abbeel +2

A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce…