config: set q_gap_threshold=0.1 as default — force trade selectivity

Q-gap was 0.0 (disabled) meaning the model traded on every bar regardless
of conviction. With 0.1, the model must have Q(best) - Q(flat) > 0.1
before entering a position. Local test showed 21% fewer trades.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

config/training/dqn-hyperopt.toml

@@ -81,7 +81,7 @@ w_idle = 0.01
 dd_threshold = 0.01
 loss_aversion = 1.5
 time_decay_rate = 0.0005
-q_gap_threshold = 0.0
+q_gap_threshold = 0.1
 
 [fixed]
 use_branching = true                   # GPU pipeline requires branching
@@ -113,4 +113,4 @@ w_idle = 0.01
 dd_threshold = 0.01
 loss_aversion = 1.5
 time_decay_rate = 0.0005
-q_gap_threshold = 0.0
+q_gap_threshold = 0.1

config/training/dqn-production.toml

@@ -72,4 +72,4 @@ w_idle = 0.01
 dd_threshold = 0.01
 loss_aversion = 1.5
 time_decay_rate = 0.0005
-q_gap_threshold = 0.0               # disabled by default — hyperopt searches [0.0, 0.5]
+q_gap_threshold = 0.1               # trade only with conviction — hyperopt searches [0.0, 0.5]

config/training/dqn-smoketest.toml

@@ -36,4 +36,4 @@ w_idle = 0.01
 dd_threshold = 0.01
 loss_aversion = 1.5
 time_decay_rate = 0.0005
-q_gap_threshold = 0.0
+q_gap_threshold = 0.1

crates/ml/src/hyperopt/adapters/dqn.rs

@@ -3931,7 +3931,7 @@ mod tests {
         assert_eq!(bounds[35], (0.01, 0.01));     // dd_threshold (FIXED in Fast phase)
         assert_eq!(bounds[36], (1.5, 1.5));       // loss_aversion (FIXED in Fast phase)
         assert_eq!(bounds[37], (0.0005, 0.0005)); // time_decay_rate (FIXED in Fast phase)
-        assert_eq!(bounds[38], (0.0, 0.0));       // q_gap_threshold (FIXED in Fast phase)
+        assert_eq!(bounds[38], (0.1, 0.1));       // q_gap_threshold (FIXED in Fast phase)
     }
 
     #[test]