feat: activate all dormant feature defaults + verify Kelly sizing

- DQNHyperparameters::conservative(): q_gap_threshold 0.0→0.05 (Tier 2 conviction gating active)
- DQNHyperparameters::conservative(): her_ratio 0.0→0.2 (20% HER relabeling enabled)
- All other Tier 2 defaults already active: count_bonus_coefficient=Some(0.1),
  curiosity_weight=0.1, use_cql=true, cql_alpha=0.1, enable_kelly_sizing=true,
  kelly_fractional=0.5, kelly_max_fraction=0.25
- Kelly sizing in experience_kernels.cu confirmed active: ps[14:17] wired,
  f*=(b*p-q)/b formula correct, half-Kelly safety applied, total_trades>=20 gate present

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

crates/ml/src/trainers/dqn/config.rs

@@ -1317,7 +1317,7 @@ impl DQNHyperparameters {
             dd_threshold: 0.02,
             loss_aversion: 1.5,
             time_decay_rate: 0.0005,
-            q_gap_threshold: 0.0, // disabled by default — hyperopt can search [0.0, 0.5]
+            q_gap_threshold: 0.05, // Tier 2 default: mild conviction gating (hyperopt searches [0.0, 0.5])
             use_huber_loss: true, // Default: Huber loss enabled (more robust)
             huber_delta: 100.0,   // BUG #12 FIX: Scale delta 100x for gradient explosion fix (was 1.0)
             use_double_dqn: true, // Default: Double DQN enabled (prevents overestimation bias)
@@ -1444,7 +1444,7 @@ impl DQNHyperparameters {
             dropout_anneal_steps: 10000,          // Default: 10K steps for annealing
 
             // P1.7: Hindsight Experience Replay
-            her_ratio: 0.0,                       // Default: disabled (hyperopt will tune 0.0-0.8)
+            her_ratio: 0.2,                       // Tier 2 default: 20% HER relabeling (hyperopt tunes 0.0-0.8)
             her_strategy: "future".to_owned(),   // Default: future strategy (better than final)
 
             // P1.9: Generalized Advantage Estimation