
Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
Is There a Reversible State?
Most of the things that we do as people are reversible most of the time. It's essentially like, I mean, we binned our environment and the infrastructure around us to make sure that we don't do irreversible things. And there's a dynamic programming style effect where states close to our irreversible state have become much state. Like safety is about being able to gay the world back to the previous state or something.
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.