High-Level Planning
Current AI excels in virtual environments but struggles with real-world applications. While robots typically rely on simulations, the approach discussed emphasizes learning through direct experimentation, akin to how a child learns. This method aims to develop a deeper understanding of industrial processes by generating experiments that yield valuable data for model improvement.In this clip
From this podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Upside-Down Reinforcement Learning with Jürgen Schmidhuber - #357
Related Questions