TalkRL: The Reinforcement Learning Podcast cover image

Jordan Terry

TalkRL: The Reinforcement Learning Podcast

00:00

The Jumpy Wrapper Road Map

Sarter is going to have this really weird property right now, environments. Numpi tensers rase tineral networks to use and eve in every differentdeep learning libraec just natively inter opithos. However, you're ging to be rtrning data structures other than numpi,. becase numpi native run on the gpu. And so you have to have the wrappers wrtin a way that they, for example, can handle both jacks and numpi environments. Sont, we need to do rapper gad anyways.

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