foxhunt

Files

jgrusewski 03062f2401 fix(ml): use exposure index (0-4) in DQN experience storage and tracking

FactoredAction::to_index() returns 0-44 (exposure×9 + order×3 + urgency),
but DQN Q-network has 5 outputs. Storing the factored index in Experience
caused train_step() to reject valid actions (e.g. Flat→index 19 > num_actions=5).

Fix: use action.exposure as usize (0-4) for:
- Experience storage (training loop + validation adapter)
- Count bonus tracking (diversity metrics)
- Safety action counts (diversity monitor)
- Debug logging (action indices)
- Test assertions (< 45 → < 5)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-06 16:27:17 +01:00

adapters.rs

fix(ml): use exposure index (0-4) in DQN experience storage and tracking

2026-03-06 16:27:17 +01:00

degradation.rs

refactor: restructure repo — crates/, bin/, testing/ layout

2026-02-25 11:56:00 +01:00

financial.rs

refactor: restructure repo — crates/, bin/, testing/ layout

2026-02-25 11:56:00 +01:00

harness.rs

refactor: restructure repo — crates/, bin/, testing/ layout