这位 AI 创业者正在开发能为意外情况提前规划的 Agent

为实现这一目标，Hafner 依赖一种称为“基于模型的强化学习”（model-based reinforcement learning）的方法。他开发世界模型——旨在模拟物理现实的 AI 模型——并在这些模型中训练 Agent。Agent 本质上将该模型视为现实世界的模拟环境，并学习应如何在其中行动。随后，它利用这些经验对未来结果作出预测（用 Hafner 的说法，或许是“做梦”或“想象”）。这使 Agent——或搭载它们的机器人——能够在现实世界（IRL）中应对陌生情境。

“我有机会与 Google 的许多极其聪明的研究人员交流，而他毫无疑问位列其中最顶尖的 0.5%。”

Timothy Lillicrap，Google DeepMind

与其他尝试不同，Hafner 的技术使 Agent 及其控制的机器人能够执行极其复杂的任务，而无需采用机器人技术传统上依赖的现实世界试错式训练。

Hafner 在德国东北部的一座乡村小镇长大，父母都是古典音乐家。他从一位邻居那里学会了编程；上高中时，他开始在线学习 AI 课程，并很快对此产生了热情。“我一直着迷于思考是如何运作的，”他说。AI 为他提供了一种在计算机上模拟这一过程的方式。

2015 年，Hafner 在波茨坦哈索·普拉特纳研究所（Hasso Plattner Institute）攻读工程学本科二年级时，获得了 Google Brain 学生研究员的职位。此后，他在该公司完成了十余次实习并担任过其他职位，包括在英国、加拿大和美国的 Google Brain 与 Google DeepMind（两者此后已合并至 DeepMind）任职。他曾与业界传奇人物合作，包括常被称为 AI 教父之一的 Geoffrey Hinton，以及 Ashish Vaswani——后者是开创性论文“Attention Is All You Need”的共同作者，该论文描述了如今大语言模型所使用的 Transformer 技术。

To achieve this, Hafner relies on something called model-based reinforcement learning. He develops world models—AI models designed to emulate physical reality—and trains agents within them. The agent essentially treats the model as a real-world simulation and learns how to act there. It then uses those experiences to make predictions (to dream or imagine, Hafner might say) about future outcomes. That allows agents—or the robots they’re embedded in—to navigate unfamiliar situations IRL.

“I get to interact with a lot of really smart people in research at Google, and he easily sits in the top half of 1%.”

Timothy Lillicrap, Google DeepMind

Unlike other efforts, Hafner’s technique enables agents and the robots they control to execute massively complicated tasks without the real-world trial-and-­error training that’s traditionally been used in robotics.

Hafner grew up in a rural town in northeastern Germany, where his parents were both classical musicians. He learned programming from a neighbor, and in high school he began taking online courses about AI, which quickly developed into a passion. “I was always fascinated with how thinking works,” he says. AI offered him a way to emulate it on a computer.

In 2015, as a second-year under­graduate studying engineering at Hasso Plattner Institute in Potsdam, he won a role as a student researcher at Google Brain. From there, he went on to a dozen internships and other positions at the company, including stints with Google Brain and Google DeepMind (the two have since merged under DeepMind) in the UK, Canada, and the US. He worked with industry legends including Geoffrey Hinton, who is often referred to as one of the godfathers of AI, and Ashish Vaswani, coauthor of the groundbreaking research paper “Attention Is All You Need,” which described the transformer technology used by today’s large language models.