Files
foxhunt/crates
jgrusewski b44df39498 feat: Q-mean centering — prevents bootstrapping drift (Component 8)
Two-phase kernel: q_mean_reduce computes global mean, q_mean_subtract
centers all Q-values. Runs after compute_expected_q, before Q-attention.
Fixes Q-mean drift 0→+0.47 observed in train-vpb4w.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 08:46:35 +02:00
..