David Bombal cover image

#398: Learn AI for Free! Computerphile explains hype vs reality and how to get started.

David Bombal

00:00

Reactor Learning Is Still Supervised Learning

Sinceo a, spend a lot of time thinking about different ways you could train a network. It's just that you get the labels as you go from playing tha game. With reinforcement learning, you have to start trying to give it rewards. For me, i mean, these are fascinating because they're trained in a very different way to the way i would train ta network.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app