Transformer architectures have facilitated the development of large-scale and general-
purpose sequence models for prediction tasks in natural language processing and computer …

Inspired by progress in large-scale language modeling, we apply a similar approach
towards building a single generalist agent beyond the realm of text outputs. The agent …

A longstanding goal of the field of AI is a method for learning a highly capable, generalist
agent from diverse experience. In the subfields of vision and language, this was largely …

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 …

Human can leverage prior experience and learn novel tasks from a handful of
demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve …

Transformers, originally devised for natural language processing (NLP), have also produced
significant successes in computer vision (CV). Due to their strong expression power …

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL)
algorithms into neural networks by modeling their training histories with a causal sequence …

Several recent works have proposed a class of algorithms for the offline reinforcement
learning (RL) problem that we will refer to as return-conditioned supervised learning …

Fine-tuning reinforcement learning (RL) models has been challenging because of a lack of
large scale off-the-shelf datasets as well as high variance in transferability among different …

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the
environment. We aim to tackle a more challenging problem: learning a safe policy from an …