Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
Is There a Flaw in the Robot Design?
Sajaras: In some sense, unsupervised learning encourages what comes naturally to the robot. So if we want a robot that walks in a certain way, maybe the design needs to rank a comedy in that as well. But it's like, it's a good objective to like evolve your robots as well. Like seeing like certain designs are better than the others.
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.
