-
Asymmetric self-play for automatic goal discovery in robotic manipulation
We train a single, goal-conditioned policy that can solve many robotic m...
01/13/2021 ∙ by OpenAI OpenAI, et al. ∙
12
∙
share
read it
-
Behavior Priors for Efficient Reinforcement Learning
As we deploy reinforcement learning agents to solve increasingly challen...
10/27/2020 ∙ by Dhruva Tirumala, et al. ∙
10
∙
share
read it
-
Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning
We propose a novel meta-learning framework for real-time object tracking...
11/25/2019 ∙ by Ilchae Jung, et al. ∙
0
∙
share
read it
-
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
As reinforcement learning agents are tasked with solving more challengin...
03/18/2019 ∙ by Dhruva Tirumala, et al. ∙
20
∙
share
read it
-
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
We study how to leverage off-the-shelf visual and linguistic data to cop...
10/03/2018 ∙ by Hyeonwoo Noh, et al. ∙
0
∙
share
read it
-
Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
Overfitting is one of the most critical challenges in deep neural networ...
10/14/2017 ∙ by Hyeonwoo Noh, et al. ∙
0
∙
share
read it
-
Large-Scale Image Retrieval with Attentive Deep Local Features
We propose an attentive local feature descriptor suitable for large-scal...
12/19/2016 ∙ by Hyeonwoo Noh, et al. ∙
0
∙
share
read it
-
Training Recurrent Answering Units with Joint Loss Minimization for VQA
We propose a novel algorithm for visual question answering based on a re...
06/12/2016 ∙ by Hyeonwoo Noh, et al. ∙
0
∙
share
read it
-
Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction
We tackle image question answering (ImageQA) problem by learning a convo...
11/18/2015 ∙ by Hyeonwoo Noh, et al. ∙
0
∙
share
read it
-
Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
We propose a novel deep neural network architecture for semi-supervised ...
06/16/2015 ∙ by Seunghoon Hong, et al. ∙
0
∙
share
read it
