AIhub咖啡角:世界模型

AIhub 咖啡角通过简短的对话捕捉了人工智能专家的思考。这个月我们深入研究世界模型。它们是什么?它们有什么潜力?这次加入对话的有:Sanmay Das(弗吉尼亚理工大学)、Rina Dechter(加州大学欧文分校)、Tom Dietterich(俄勒冈州立大学)、Sabine Hauert([…] 大学)

来源:ΑΙhub

AIhub 咖啡角通过简短的对话捕捉了人工智能专家的思考。 This month we delve into world models. What are they, and what potential do they have? Joining the conversation this time are: Sanmay Das (Virginia Tech), Rina Dechter (University of California, Irvine), Tom Dietterich (Oregon State University), Sabine Hauert (University of Bristol), Michael Littman (Brown University), and Marija Slavkovik (University of Bergen).

Sabine Hauert:世界模特最近很受欢迎,并且为此投入了大量资金。 Recently, NVIDIA came to do a one-day training at the Bristol Robotics Laboratory and presented us with all their latest tools, including world models as a way to generate simulated environments that could be useful to train robot policies on.我对生成大量示例的潜力感到非常眼花缭乱,因为我认为这是机器人技术的瓶颈。我们无法利用网络上已有的大量数据来完成我们所做的某些事情。我觉得它看起来非常有用,所以我正在尝试一下。 I can’t quite figure out if it’s just extending what we do with language to video, and then pretending it has physical properties, or whether it does have this holy grail where we can generate all these environments that will be directly useful for robotics.在这次培训中,有人举手问什么是世界模型,得到的答复是它只是一个视频生成器。 Therefore, I think a good starting point for our discussion today would be to define what a world model is, because I think people are spinning it in different ways.

Sabine:我有点喜欢送货机器人场景(这是我所做的事情),而不是用这些系统进行手术。我认为有更多平凡的应用程序可能比首先处理困难的事情更富有成果。 That’ll be interesting to see.

tags:

致力于提供有关人工智能的免费高质量信息。