Unsupervised pre-training methods utilizing large and diverse datasets have achieved
tremendous success across a range of domains. Recent work has investigated such …

Both text and video data are abundant on the internet and support large-scale self-
supervised learning through next token or frame prediction. However, they have not been …

Reward-free data is abundant and contains rich prior knowledge of human behaviors, but it
is not well exploited by offline reinforcement learning (RL) algorithms. In this paper, we …

Pre-training large models on vast amounts of web data has proven to be an effective
approach for obtaining powerful, general models in several domains, including language …

Recently, people have shown that large-scale pre-training from diverse internet-scale data is
the key to building a generalist model, as witnessed in the natural language processing …

Abstract Pre-training for Reinforcement Learning (RL) with purely video data is a valuable
yet challenging problem. Although in-the-wild videos are readily available and inhere a vast …

We introduce Jafar, an open-source Jax reimplementation of Genie, a foundational world
model. Genie was the first world model trained in an unsupervised manner on unlabelled …

Imitation learning (IL) has achieved considerable success in solving complex sequential
decision-making problems. However, current IL methods mainly assume that the …

Recently, various pre-training methods have been introduced in vision-based
Reinforcement Learning (RL). However, their generalization ability remains unclear due to …

We study pre-training representations for decision-making using video data, which is
abundantly available for tasks such as game agents and software testing. Even though …