TalkRL: The Reinforcement Learning Podcast cover image

Jacob Beck and Risto Vuorio

TalkRL: The Reinforcement Learning Podcast

00:00

Metah Rl - Open a Universe

This episode is a synthesis of existing ideas than some very new concepts. iliya setsgiver was giving a talk about this um and at the time it was it was about opin ai universe. i guess rl just not powerful enough for for such a task distribution yeah that's a that's a great question. I think what we were finding here is that really like designing designing a task distribution in which you can train these like more capable agents is really is a really complicated problem.

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