“So the sum of rewards is the return, right? So like in…” — Dwarkesh Podcast at 1:30:03
“So the sum of rewards is the return, right? So like in our, now you've set up here, we only have an indicator variable for the return where either you won or lost. So in the case where you lost, well, you just don't train on your gradient as zero, you don't train on those examples.”
0:00
2:37:29