“replay buffer really should have like your, you know, the…” — Dwarkesh Podcast at 2:04:31
“replay buffer really should have like your, you know, the states that your policy would visit, plus some distribution of states that you might drift to and then how to return back to your optimal states. Yeah. Now, if you take this to the extreme and you say like, well, let's, uh, we don't have any”
0:00
2:37:29