Building a robot that can understand and learn to interact by watching humans has inspired
several vision problems. However, despite some successful results on static datasets, it …

Abstract Model-based reinforcement learning (RL) algorithms, which learn a dynamics
model from logged experience and perform conservative planning under the learned model …

Offline reinforcement learning (RL) aims to find performant policies from logged data without
further environment interaction. Model-based algorithms, which learn a model of the …

Offline reinforcement learning (RL) defines the task of learning from a static logged dataset
without continually interacting with the environment. The distribution shift between the …

If generalist robots are to operate in truly unstructured environments, they need to be able to
recognize and reason about novel objects and scenarios. Such objects and scenarios might …

Offline reinforcement learning (RL) can learn control policies from static datasets but, like
standard RL methods, it requires reward annotations for every transition. In many cases …

Learning efficiently from small amounts of data has long been the focus of model-based
reinforcement learning, both for the online case when interacting with the environment, and …

Offline reinforcement learning (RL) algorithms have shown promising results in domains
where abundant pre-collected data is available. However, prior methods focus on solving …

Offline reinforcement learning (RL) enables learning control policies by utilizing only prior
experience, without any online interaction. This can allow robots to acquire generalizable …

An agent that is capable of predicting what happens next can perform a variety of tasks
through planning with no additional training. Furthermore, such an agent can internally …