论文标题
通才代理
A Generalist Agent
论文作者
论文摘要
受大规模语言建模进度的启发，我们采用类似的方法来构建文本输出领域之外的单一通才代理。我们称为Gato的代理商是一种多模式，多任务，多任务的通才政策。具有相同权重的同一网络可以播放Atari，字幕图像，聊天，带有真正的机器人臂的堆栈块等等，根据其上下文决定是否输出文本，联合扭矩，按钮按下或其他令牌。在本报告中，我们描述了模型和数据，并记录了Gato的当前功能。
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.
