
-
Meta-Learning Requires Meta-Augmentation
Meta-learning algorithms aim to learn two components: a model that predi...
read it
-
RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real
Deep neural network based reinforcement learning (RL) can learn appropri...
read it
-
Off-Policy Evaluation via Off-Policy Classification
In this work, we consider the problem of model selection for deep reinfo...
read it
-
The Principle of Unchanged Optimality in Reinforcement Learning Generalization
Several recent papers have examined generalization in reinforcement lear...
read it
-
Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks
Real world data, especially in the domain of robotics, is notoriously co...
read it
-
Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors
Obtaining reliable uncertainty estimates of neural network predictions i...
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...
read it
-
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Deep reinforcement learning has achieved many recent successes, but our ...
read it
-
Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
Instrumenting and collecting annotated visual grasping datasets to train...
read it
-
Learning Hierarchical Information Flow with Recurrent Neural Modules
We propose ThalNet, a deep learning model inspired by neocortical commun...
read it