TalkRL: The Reinforcement Learning Podcast cover image

Rohin Shah

TalkRL: The Reinforcement Learning Podcast

00:00

The Highest Level of Task Complexity in Deep Learning

Learnings paradine the query as an action in the actpus. So i i really like the you laid out some levels of task complexity, and i'm just going to go through them really briefly. For simpler tasks, would be specifying what the task is a and the machine figures it, hoto do it. And then the for harder tasks, specifying task is difficult, so the agent can lear, may learn a reward function from human feedback. How do you see this latter? Is this a universal, a classification scheme? Are we dan at the highest level?

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