ML 021: Grokking Deep Reinforcement Learning with Miguel Morales
Adventures in Machine Learning
00:00
Is Reactor Learning Really a Good Idea?
I remember looking at that and the explanation that I got was essentially, yeah, that the AI figured out that it needed to make moves and it did things that, yeah, human just would never do. Right? And how does it work in an actual algorithm, right? How do you tell it that it's good or telling it that it’s bad? He says he goes through these concepts like one step at a time; his new book is 250 pages long.
Transcript
Play full episode
