
Yoshua Bengio: Deep Learning
Lex Fridman Podcast
00:00
How Did You Get Hooked With Artificial Intelligence?
Gans or other gientif models will be crucial ingredients in building agents that can understand d a lot of the successes in reenforcement learning in the past has been with a policy gradient whereyo, you'll just learn a policy. But there are lots of issues with that, and we don't know how to do model bays a al right now. i think this is where we have to go in order to build models that can jornlize faster and better.
Transcript
Play full episode