activity
20172022
most citedPI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale

3 citations · 4 across the 2 of their papers we have counts for

collaborators

6 papers

cs.RO20223 cited

PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale

Kuang-Huei Lee, Ted Xiao, Adrian Li +3

The predictive information, the mutual information between the past and future, has been shown to be a useful representation learning auxiliary loss for training reinforcement lear…

cs.LG2019

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

Allan Zhou, Eric Jang, Daniel Kappler +7

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations.…

cs.CV2019

Generalized Feedback Loop for Joint Hand-Object Pose Estimation

Markus Oberweger, Paul Wohlhart, Vincent Lepetit

We propose an approach to estimating the 3D pose of a hand, possibly handling an object, given a depth image. We show that we can correct the mistakes made by a Convolutional Neura…

cs.RO2018

Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks

Stephen James, Paul Wohlhart, Mrinal Kalakrishnan +6

Real world data, especially in the domain of robotics, is notoriously costly to collect. One way to circumvent this can be to leverage the power of simulation to produce large amou…

cs.CV2017

On Pre-Trained Image Features and Synthetic Images for Deep Learning

Stefan Hinterstoisser, Vincent Lepetit, Paul Wohlhart +1

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is there…

cs.LG20171 cited

Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping

Konstantinos Bousmalis, Alex Irpan, Paul Wohlhart +9

Instrumenting and collecting annotated visual grasping datasets to train modern machine learning algorithms can be extremely time-consuming and expensive. An appealing alternative…