Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
How Robust Is Quail?
Quail was trained on a variety of tasks. It can still take several thousands of steps to like actually solve the task. What do we need to add in here to make it go even faster is an interesting question. We have just barely started to scratch the surface of this.
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.
