A Generalist Agent

TL;DR

Gato is a versatile generalist agent capable of performing multiple tasks across different modalities and embodiments using a single neural network trained on diverse data, demonstrating broad applicability beyond text.

Contribution

This work introduces Gato, a unified multi-modal, multi-task, multi-embodiment agent that can handle various tasks with a single model, advancing generalist AI development.

Findings

Gato can play Atari, caption images, chat, and control robots.

The same network adapts to different modalities and outputs.

Gato demonstrates broad task versatility with a unified architecture.

Abstract

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, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. In this report we describe the model and the data, and document the current capabilities of Gato.