Four: Brian Christian on artificial intelligence
Effective Altruism: Ten Global Problems – 80000 Hours
00:00
The Problem of Sparse Rewards
The next section of the book is about a kind of shaping the behavior of o ai. There's a great story in the book about some kind of simulated animals that suffer issue hen heyr geting, sparse to reward. And so they have to evolve to figure out how to behave given that. Canyou can you tel us about that one? Yes. This is this classic study from the early nineties by dave ackley and michael whitman. They were interested in the interaction of evolution and learning.
Transcript
Play full episode
