Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
Unsupervised Reinforcement Learning
A lot of what the research I'm doing is very much motivated like team out of XM observations and best project. So a big like reason why I wanted to do unsupervised reinforcement learning was that it's truly unsupervised. But it turns out in the process, this is as mentioned, I was learning or reinforced learning as well. And my goal and I said is truly, truly get to truly adopt much and unsupervised agents.
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.
