foxhunt

Files

jgrusewski 19e5cde91e docs(sp5): Layer A close-out — replace stale scratch-buf comment

Code-quality review of A8 caught that gpu_dqn_trainer.rs:15154 still
read `// to SP5_SCRATCH_TOTAL (103) = 71 + 16 (q_branch_stats) + 16
(pearl_1_atom)` — pre-existing from A1 that wasn't updated as the
constant grew through A2-A8 (103 → 111 → 131 → 171 → 199 → 203 → 207).
The runtime allocation is correct (uses the constant, not the literal),
so this was readability-only.

Replaced the 2-line stale comment with the complete scratch-buffer
layout map covering all SP5 Layer A producer outputs:

  [0..71)    SP4 producers
  [71..87)   q_branch_stats        (Pearl 1 / A1)
  [87..103)  pearl_1_atom_update   (Pearl 1 / A1)
  [103..107) pearl_3_sigma σ       (Pearl 3 / A2)
  [107..111) pearl_3_sigma SF      (Pearl 3 / A2)
  [111..131) pearl_2_budget        (Pearl 2 / A3)
  [131..147) pearl_4 cosine + l2   (auxiliary, A4)
  [147..171) pearl_4 β1/β2/ε       (Pearl 4 / A4)
  [171..199) pearl_5 skew/kurt+τ   (Pearl 5 / A5)
  Pearl 6 (A6) writes directly to ISV — no scratch.
  [199..203) pearl_8 trail_dist    (Pearl 8 / A7)
  [203..207) pearl_1-ext num_atoms (Pearl 1-ext / A8)

Closes the last residual A1-vintage comment debt; gives Layer B
implementers a self-contained map of the scratch contract.

Comment-only change. cargo check clean.

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

2026-05-02 00:26:43 +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(sp5): comprehensive implementation plan — 4 layers, ~21 tasks

2026-05-01 20:01:27 +02:00

dqn-backward-nan-audit.md

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