Reinforcement learning (RL) has emerged as a powerful paradigm for
fine-...
We present a novel observation about the behavior of offline reinforceme...
Modern decision-making systems, from robots to web recommendation engine...
Learning to control an agent from data collected offline in a rich
pixel...
Safety is a crucial necessity in many applications of reinforcement lear...
A person walking along a city street who tries to model all aspects of t...
In real-world reinforcement learning applications the learner's observat...
We study reinforcement learning (RL) in settings where observations are
...
Contrastive learning is a popular form of self-supervised learning that
...
Many real-world applications of reinforcement learning (RL) require the ...
Noise contrastive learning is a popular technique for unsupervised
repre...
Topic models are widely used in studying social phenomena. We conduct a
...
We present a novel interactive learning protocol that enables training
r...
We introduce a new problem setting for continuous control called the LQR...
We present an algorithm, HOMER, for exploration and reinforcement learni...
Model-based reinforcement learning is an appealing framework for creatin...
We study the problem of jointly reasoning about language and vision thro...
Increasingly, perceptual systems are being codified as strict pipelines
...
We propose an approach for mapping natural language instructions and raw...
When environmental interaction is expensive, model-based reinforcement
l...
Semantic parsing from denotations faces two key challenges in model trai...
We propose to decompose instruction execution to goal prediction and act...
Learning a generative model is a key component of model-based reinforcem...
Model-based reinforcement-learning methods learn transition and reward m...
We present CHALET, a 3D house simulator with support for navigation and
...
We propose to directly map raw visual observations and text input to act...