Rank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic
SAC study finds early |Q| growth predicts value-divergence flags, while rank collapse stays recoverable.
1 stories, newest first · one card per story
SAC study finds early |Q| growth predicts value-divergence flags, while rank collapse stays recoverable.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views