foxhunt

Files

jgrusewski 6994b9cf97 docs(dqn): SP1 Phase A — backward NaN audit

Read-only γ audit of every backward-path kernel writing to bw_d_h_s2 /
grad_buf / save_h_s2 accumulators. Per-kernel inventory against
unsafe-pattern checklist (sqrtf-neg, 1/0, logf-≤0, expf-large, EMA
variance, atomicAdd/saxpy NaN-propagation). Each section includes:
identified pattern + line citation, severity, proposed guard form,
ISV bound option, F0 risk, Phase B flag-slot allocation.

Cross-referenced session_2026-04-05_nan_investigation.md residual 8%
step-2 NaN in apply_iqn_trunk_gradient — never closed; ranked top
suspect for SP1.

Output drives SP1 Phase B (12 new flag slots in nan_flags_buf 24→48)
and Phase C surgical fix(es). Durable artifact for SP2 framework
codification + SP3 structural-fix scoping.

2026-04-29 23:35:29 +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

plan(dqn): SP1 numerical stability — F1 NaN root-cause investigation

2026-04-29 23:21:26 +02:00

dqn-backward-nan-audit.md

docs(dqn): SP1 Phase A — backward NaN audit