AI 译本 · Equalang
新上架PDF · 2026年11月翻译
加载中…
加载中…
TMLR · 2023
通用型智能体
Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gomez Colmenarejo et al.
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.
受大规模语言建模领域进展的启发，我们采用类似的方法，尝试打造一个超越文本输出范畴的单一通用型智能体。我们将这个智能体称为 Gato，它是一种多模态、多任务、适用于多种具身形态的通用策略。借助同一个网络和同一组权重，Gato 可以玩 Atari 游戏、为图像生成说明文字、进行对话，还能操控真实机械臂堆叠积木，等等。它会根据上下文决定输出文本、关节扭矩、按钮操作或其他令牌。本报告介绍了 Gato 的模型和数据，并记录了它目前具备的能力。
PDF · 2026年11月翻译