foxhunt

Files

jgrusewski defbd0abe1 spec(sp19+20): patch 7 review issues

P1 (must-fix bugs/gaps):
1. ASYM_RATIO_INDEX → LOSS_CAP_INDEX with explicit formula in §4.1 and §4.5
   (was double source-of-truth — formula in §4.1, ISV slot orphaned)
2. Replay buffer schema change (per-bar aux_conf) added to §8 implementation
   footprint (~50 LoC additional, was invisible in original spec)
3. hold_baseline_buffer size specified = LOOKAHEAD_HORIZON_MAX = 30 bars (§4.2)
4. "4-tier gate" typo → "5-tier gate" in §7

P2 (clarifications):
5. alpha_ema centering documented as load-bearing for cold-start learning (§4.1)
   — not just for Q-target stability. EV is slightly negative at WR=46% with
   uninformed SP19 label; advantage-style centering rescues cold-start.
6. Q-scale asymmetry between Hold (uncentered) and trade (alpha_ema centered)
   documented as INTENTIONAL design choice (§4.2) — produces marginal
   Q(trade) > Q(Hold) preference that counteracts the Q(Hold) attractor.
   Behavioral test sp20_pure_noise validates the no-signal Hold default still works.

P3 (tightening):
7. Behavioral test thresholds tightened (§4.6):
   - sp20_pure_trend: WR > 70% → > 90%, PF > 2.0 → > 3.0
   - sp20_pure_noise: Hold% > 80% → > 95%, trades < 50 → < 20

2026-05-09 17:35:36 +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

spec(sp19+20): patch 7 review issues

2026-05-09 17:35:36 +02:00

dqn-backward-nan-audit.md

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