Skip to content

“then it's intractable. There isn't enough reward signal…” — Invisible Machines podcast by UX Magazine at 18:12

“then it's intractable. There isn't enough reward signal for the reinforcement learning to work. And so what's exciting now, I think, is that they're going back to simulations. And nine years on from that time when they had a setback, maybe it's going to work. Yeah, it was about getting the right amounts of each…”

0:00 1:00:18