jgrusewski
c1b6848c21
feat(dqn-v2): C.6 Task 10 — gamma GPU kernel + CPU monitor (discount factor)
gamma_update kernel computes health-coupled gamma from ISV[LEARNING_HEALTH=12]:
gamma_eff = gamma_min + (gamma_base - gamma_min) * health. Single-thread
cold-path kernel writes ISV[GAMMA_EFF_INDEX=43].
GammaMonitor is a read-only observer exposing gamma_eff, health, fire_rate.
Consumer migration: fill_gamma_buf and IQL gamma computation now read
ISV[GAMMA_EFF_INDEX] via read_isv_signal_at (pinned, zero-copy). Training
loop passes hyperparams.gamma as gamma_base to the kernel.
Deleted: apply_adaptive_gamma method (GpuDqnTrainer + FusedTrainingCtx
delegates), set_adaptive_gamma method, adaptive_gamma field (GpuDqnTrainer
+ DQNTrainer), last_gamma_eff cached field + last_gamma_eff() delegate.
StateResetRegistry entry for adaptive_gamma removed (field gone).
Smoke test generalization.rs updated to check config gamma_base instead
of deleted adaptive_gamma field.
Tests: 3 monitor unit tests pass. cargo check -p ml at 8-warning baseline.
Plan 1 Task 10. Spec §4.C.6 (2026-04-24 revision).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-24 18:05:44 +02:00
..
2026-04-23 08:35:27 +02:00
2026-04-23 08:37:44 +02:00
2026-04-23 08:38:44 +02:00
2026-04-24 18:05:44 +02:00
2026-04-23 08:35:27 +02:00
2026-04-24 11:37:00 +02:00
2026-04-23 10:19:56 +02:00
2026-04-23 10:35:48 +02:00
2026-04-23 08:35:27 +02:00
2026-04-23 08:35:27 +02:00
2026-04-18 10:19:12 +02:00
2026-04-23 10:09:15 +02:00
2026-04-23 08:44:05 +02:00
2026-04-23 08:44:05 +02:00