“Early on in training, when the value network hasn't…” — Dwarkesh Podcast at 1:07:55
“Early on in training, when the value network hasn't involved trained on finished games, that MCTS is worse than randomization policy. So is it just like a heuristic that MCTS is better than policy or is that like, is there some guarantee? Right. In practice, it is a heuristic and it”
0:00
2:37:29