Pieter Abbeel: Deep Reinforcement Learning
Lex Fridman Podcast
00:00
Are You a Mathematician or an Empirical Trial in an Error?
CNN's John Sutter asks whether you prefer math or empirical trial in an error for the discovery of the essence of what it means to do something intelligent. "If you have something you can mathematically formalize, you can leapfrog a lot of experimentation," he says. But experiments take time and progress has not been able to find the math that allows it to leapfrog ahead,. He adds: "Unfortunately, not so much yet"
Transcript
Play full episode
