“You, you compute Q of S prime and you find the action that…” — Dwarkesh Podcast at 2:08:24
“You, you compute Q of S prime and you find the action that should go with S prime that makes this Q value as high as possible. And then you add that to the reward here. And that gives you your actual target. Right. So for this current S and A, your Q target is this. So now you have a, now you send”
0:00
2:37:29