Eric Jang

is this you? claim profile

0 followers
Google

RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer

The success of deep reinforcement learning (RL) and imitation learning (...
11/06/2020 ∙ by Daniel Ho, et al. ∙ 0 ∙ share

read it
Meta-Learning Requires Meta-Augmentation

Meta-learning algorithms aim to learn two components: a model that predi...
07/10/2020 ∙ by Janarthanan Rajendran, et al. ∙ 5 ∙ share

read it
Thinking While Moving: Deep Reinforcement Learning with Concurrent Control

We study reinforcement learning in settings where sampling an action fro...
04/13/2020 ∙ by Ted Xiao, et al. ∙ 17 ∙ share

read it
Scalable Multi-Task Imitation Learning with Autonomous Improvement

While robot learning has demonstrated promising results for enabling rob...
02/25/2020 ∙ by Avi Singh, et al. ∙ 0 ∙ share

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

Imitation learning allows agents to learn complex behaviors from demonst...
06/07/2019 ∙ by Allan Zhou, et al. ∙ 1 ∙ share

read it
Grasp2Vec: Learning Object Representations from Self-Supervised Grasping

Well structured visual representations can make robot learning faster an...
11/16/2018 ∙ by Eric Jang, et al. ∙ 26 ∙ share

read it
Generative Ensembles for Robust Anomaly Detection

Deep generative models are capable of learning probability distributions...
10/02/2018 ∙ by Hyunsun Choi, et al. ∙ 6 ∙ share

read it
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation

In this paper, we study the problem of learning vision-based dynamic man...
06/27/2018 ∙ by Dmitry Kalashnikov, et al. ∙ 0 ∙ share

read it
Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods

In this paper, we explore deep reinforcement learning algorithms for vis...
02/28/2018 ∙ by Deirdre Quillen, et al. ∙ 0 ∙ share

read it
Sim2Real View Invariant Visual Servoing by Recurrent Control

Humans are remarkably proficient at controlling their limbs and tools fr...
12/20/2017 ∙ by Fereshteh Sadeghi, et al. ∙ 0 ∙ share

read it
End-to-End Learning of Semantic Grasping

We consider the task of semantic robotic grasping, in which a robot pick...
07/06/2017 ∙ by Eric Jang, et al. ∙ 0 ∙ share

read it
Categorical Reparameterization with Gumbel-Softmax

Categorical variables are a natural choice for representing discrete str...
11/03/2016 ∙ by Eric Jang, et al. ∙ 0 ∙ share

read it

Eric Jang

Featured Co-authors

Sergey Levine

Chelsea Finn

Ofir Nachum

Ben Poole

Alexander Toshev

Shixiang Gu

Julian Ibarz

Karol Hausman

Kanishka Rao

Vincent Vanhoucke

Avi Singh

RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer

Meta-Learning Requires Meta-Augmentation

Thinking While Moving: Deep Reinforcement Learning with Concurrent Control

Scalable Multi-Task Imitation Learning with Autonomous Improvement

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

Grasp2Vec: Learning Object Representations from Self-Supervised Grasping

Generative Ensembles for Robust Anomaly Detection

QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods

Sim2Real View Invariant Visual Servoing by Recurrent Control

End-to-End Learning of Semantic Grasping

Categorical Reparameterization with Gumbel-Softmax