foxhunt

Files

jgrusewski d6bfad7033 docs(sp20): consolidate Phase 5 audit-doc + close-out

Replaces the per-commit audit-doc entries from commits 1-3 with a single
consolidated Phase 5 close-out entry. The consolidated entry covers:

  - The full design rationale: gate the REWARD (not the target); avoids
    needing q_mean_a entirely. At low aux confidence, r_used → 0 ⇒
    Bellman target collapses to gamma * Q(s', a').
  - All 5 components: trainer buffer, FusedTrainerCtx accessor, training
    loop wire-up, kernel signature + gate, launcher arg.
  - NULL-tolerance contract: aux_conf_at_state == NULL OR isv_signals
    == NULL ⇒ gate = 1.0 (identity).
  - Default-state semantics: alloc_zeros 0.0 sentinel → gate ≈ 0.12 →
    reward mostly suppressed pre-population (graceful degradation).
  - reward_bias interaction (composes cleanly — gate damps reward
    pre-projection, reward_bias lifts target Q-mean per-branch).
  - Plan accuracy errata: the user spec's "add aux_conf_at_state_buf
    field to GpuBatch struct" was unnecessary — GpuBatch doesn't
    carry the SP13 B1.1b aux_sign_labels_ptr either; both follow the
    "trainer-only buffer + direct-gather" pattern.
  - Test coverage: 3 CPU math tests + 1 GPU behavioral integration test.
  - Confidence: medium-high that the gate fires correctly on real data;
    end-to-end smoke validation deferred (no smokes dispatched per
    controller instruction).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-10 14:54:41 +02:00

infra

feat(infra): GPU training launcher with local/cloud routing

2026-02-23 11:19:58 +01:00

plans

feat(dqn): enable Branching DQN with 45 factored actions (5×3×3)

2026-03-11 22:00:13 +01:00

superpowers

docs(sp20): plan accuracy errata for Phase 2 (Tasks 2.0/2.1/2.2/2.3/2.4)

2026-05-10 00:30:33 +02:00

dqn-backward-nan-audit.md

fix(dqn): SP3 Mech 10 — ISV-driven h_s2 activation clamp + slot 49 diag