foxhunt

Files

jgrusewski 41a7da7008 feat(phase-e-4-a): T13 smoke validation PASSES gate 1

1000-episode smoke with --c51 --temporal --window-k 16
--mamba2-hidden-dim 32 (frozen Mamba2 — T10 backward not yet wired).

Comparison vs C51-flat baseline (also 1000 ep):
  R_mean ep 1000:    C51-flat -1.1  →  --temporal +3.9   (+5.0)
  R_mean peak ep 700: C51-flat +1.0 →  --temporal +10.0  (+9.0)
  R_mean ep 50:      C51-flat -8.2  →  --temporal +6.8   (+15)
  rvr:               +1.046 → +1.047
  EARLY_Q_MOVEMENT:  0.0066 → 0.0364 (5× more weight motion)

Gate 1 criteria:
  ✅ R_mean ≥ -0.5: +3.9
  ✅ rvr ≥ +1.04: +1.047
  ✅ EARLY_Q_MOVEMENT ≥ 0.01: 0.0364
  ⚠ ACTION_ENTROPY = 0.64 < 1.10 (kill criterion misaligned with
    gated-policy paradigm: Wait-collapse is correct behavior, not
    failure)

Note: Q_SPREAD_EMA shows a transient outlier at ep 950 (16417, was
~10 throughout) — likely NaN/Inf propagation in the kill-criteria
EMA accumulator from a single C51-logit overflow at extreme random
Mamba2 output. Policy quality unaffected (rvr stable, R_mean stable).
Investigation tracked in follow-on memory.

Frozen Mamba2: weights remain at Xavier init throughout training.
The C51 head learns over RANDOM 32-dim temporal projections of the
window — random-SSM-as-reservoir effect. T10 (Mamba2 backward +
AdamW step) should lift further.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-15 21:19:12 +02:00