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 …

Intelligent agents need to generalize from past experience to achieve goals in complex
environments. World models facilitate such generalization and allow learning behaviors …

The Arcade Learning Environment (ALE) is a popular platform for evaluating reinforcement
learning agents. Much of the appeal comes from the fact that Atari games demonstrate …

Deep reinforcement learning~(RL) has achieved remarkable successes in complex single-
task settings. However, designing RL agents that can learn multiple tasks and leverage prior …

Model-free reinforcement learning (RL) can be used to learn effective policies for complex
tasks, such as Atari games, even from image observations. However, this typically requires …

Decision Transformers (DT) have drawn upon the success of Transformers by abstracting
Reinforcement Learning as a target-return-conditioned, sequence modeling problem. In our …

Large transformer models powered by diverse data and model scale have dominated
natural language modeling and computer vision and pushed the frontier of multiple AI areas …

To solve complex real-world problems with reinforcement learning, we cannot rely on
manually specified reward functions. Instead, we need humans to communicate an objective …

Recent reinforcement learning (RL) approaches have shown strong performance in complex
domains such as Atari games, but are often highly sample inefficient. A common approach to …

Atari games have been a long-standing benchmark in the reinforcement learning (RL)
community for the past decade. This benchmark was proposed to test general competency …