Imitation learning holds tremendous promise in learning policies efficie...
We introduce Contrastive Intrinsic Control (CIC), an algorithm for
unsup...
Recent progress in deep learning has relied on access to large and diver...
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to s...
We present DrQ-v2, a model-free reinforcement learning (RL) algorithm fo...
Learning effective representations in image-based environments is crucia...
Navigation policies are commonly learned on idealized cylinder agents in...
Model-based reinforcement learning approaches add explicit domain knowle...
Deep reinforcement learning (RL) agents often fail to generalize to unse...
We propose a simple data augmentation technique that can be applied to
s...
Adaptive optimization algorithms such as Adam (Kingma Ba, 2014) are ...
Many (but not all) approaches self-qualifying as "meta-learning" in deep...
Training an agent to solve control tasks directly from high-dimensional
...
We study the Cross-Entropy Method (CEM) for the non-convex optimization ...
We explore using latent natural language instructions as an expressive a...
Momentum-based acceleration of stochastic gradient descent (SGD) is wide...
End-to-end models for strategic dialogue are challenging to train, becau...
Much of human dialogue occurs in semi-cooperative settings, where agents...
The prevalent approach to sequence to sequence learning maps an input
se...