
Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
Learning a Gun Like Optimization to Decide Whether a State Is Visited by an Expert or by Your Boss
I feel like a lot of the papers, like the core idea is very simple. It's high pranks. But yeah, I mean, that's what I like talking to people listening to the docs and like kind of sharing the works directly from them off a bit much faster. Yeah. Well, like going back. When I was younger, like I usually do like this, the good thing pens and then put it back together. Your example is you're writing me of that. That's amazing. And very specific pen. So only pen. You apart every time. Like you like take part of it off. Oh my gosh! What are your thoughts on how humans learn?
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.