
Mastering Visual Continuous Control: Improved DataAugmented Reinforcement Learning
We present DrQv2, a modelfree reinforcement learning (RL) algorithm fo...
read it

Reinforcement Learning with Prototypical Representations
Learning effective representations in imagebased environments is crucia...
read it

Learning Navigation Skills for Legged Robots with Learned Robot Embeddings
Navigation policies are commonly learned on idealized cylinder agents in...
read it

On the modelbased stochastic value gradient for continuous reinforcement learning
Modelbased reinforcement learning approaches add explicit domain knowle...
read it

Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
Deep reinforcement learning (RL) agents often fail to generalize to unse...
read it

Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
We propose a simple data augmentation technique that can be applied to s...
read it

On the adequacy of untuned warmup for adaptive optimization
Adaptive optimization algorithms such as Adam (Kingma Ba, 2014) are ...
read it

Generalized Inner Loop MetaLearning
Many (but not all) approaches selfqualifying as "metalearning" in deep...
read it

Improving Sample Efficiency in ModelFree Reinforcement Learning from Images
Training an agent to solve control tasks directly from highdimensional ...
read it

The Differentiable CrossEntropy Method
We study the CrossEntropy Method (CEM) for the nonconvex optimization ...
read it

Hierarchical Decision Making by Generating and Following Natural Language Instructions
We explore using latent natural language instructions as an expressive a...
read it

Quasihyperbolic momentum and Adam for deep learning
Momentumbased acceleration of stochastic gradient descent (SGD) is wide...
read it

Hierarchical Text Generation and Planning for Strategic Dialogue
Endtoend models for strategic dialogue are challenging to train, becau...
read it

Deal or No Deal? EndtoEnd Learning for Negotiation Dialogues
Much of human dialogue occurs in semicooperative settings, where agents...
read it

Convolutional Sequence to Sequence Learning
The prevalent approach to sequence to sequence learning maps an input se...
read it
Denis Yarats
is this you? claim profile