“value function, the search will kind of give us a better…” — Dwarkesh Podcast at 1:39:12
“value function, the search will kind of give us a better result in our initial guess. In, um, in a game where you can't easily simulate a search process, what they do instead is train what is known as a best response policy. So you fix your opponent. So let's say you're, you're currently”
0:00
2:37:29