10-component design to fix 82% Flat/Small action concentration:
1. Collapse degenerate 9→7 level exposure space
2. Per-branch reward decomposition (direction/magnitude/order/urgency)
3. Hindsight action relabeling for magnitude
4. Position-aware temporal exploration with per-branch epsilon
5. IQN quantile spread as anti-collapse signal
6. Activate PopArt + couple with tau reset
7. Feed the gradient vaccine with diverse batches
8. Per-branch bottleneck widths
9. Ensemble variance at inference
10. Clear PER between folds
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
553289545a