
Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
Learning Robotics
I was going to ask you about some of the papers that came after dads. So you mentioned the long-based approach at NeurIPS 2021. And then more recently, you've had, I think, you only live once, which I thought was really cool. Yeah. Did you want to talk about some of these papers and kind of maybe like maybe in order of like how you're thinking evolved from one to another? You only have one is a very experimental paper as well. It's very, very new.
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.