Yes, I realised that this was a downfall of n.c.p. It’s helpful for shorter rollouts, but once they get longer they can get into a kind of “probabilistic groove” which starts to unhelpfully inflate n.c.p. In mode collapse loops, n.c.p. tends to 1. So yeah, good observation.
Yes, I realised that this was a downfall of n.c.p. It’s helpful for shorter rollouts, but once they get longer they can get into a kind of “probabilistic groove” which starts to unhelpfully inflate n.c.p. In mode collapse loops, n.c.p. tends to 1. So yeah, good observation.