With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …

The human ability to learn, generalize, and control complex manipulation tasks through multi-
modality feedback suggests a unique capability, which we refer to as dexterity intelligence …

Model-based reinforcement learning methods often use learning only for the purpose of
estimating an approximate dynamics model, offloading the rest of the decision-making work …

We provide a theoretical framework for Reinforcement Learning with Human Feedback
(RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry …

Recent improvements in conditional generative modeling have made it possible to generate
high-quality images from language descriptions alone. We investigate whether these …

Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously
collected static dataset, is an important paradigm of RL. Standard RL methods often perform …

Reinforcement learning (RL) is typically viewed as the problem of estimating single-step
policies (for model-free RL) or single-step models (for model-based RL), leveraging the …

In this work, we present a scalable reinforcement learning method for training multi-task
policies from large offline datasets that can leverage both human demonstrations and …

We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors
designed to facilitate research in scalable robot learning. BridgeData V2 contains 53,896 …

Sample efficiency and exploration remain major challenges in online reinforcement learning
(RL). A powerful approach that can be applied to address these issues is the inclusion of …