TalkRL: The Reinforcement Learning Podcast cover image

Jordan Terry

TalkRL: The Reinforcement Learning Podcast

00:00

The Limits of a Custom Agent

There are like four ways of doing it. One is to go and um and use things like pie cootor or whatever, and y use pitand bonnies to all coot an. Un the easiest one is ov annumpi base environt an just right in jacks. Then, if you have c base environments, you can either modify the c base environment omto essentially compiled, orcuta. And so you end up having to have these wrappers. Will be built in a gem ther people work in this,. But you'l e u having to have, you like, wrapping whatever, a g p tenser. This is out putting to a torch tens

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