diff --git a/crates/ml/src/dqn/reward.rs b/crates/ml/src/dqn/reward.rs
index cdba24ac1..2d0f22bec 100644
--- a/crates/ml/src/dqn/reward.rs
+++ b/crates/ml/src/dqn/reward.rs
@@ -926,13 +926,9 @@ impl RewardFunction {
         // |ln(P_{t+1} / P_t)| measures the magnitude of the price change (velocity)
         let volatility = next_log_return.abs();
 
-        // BUG FIX: Scale hold_penalty_weight to percentage units
-        // Config value: 0.5-2.0 (raw scalar from hyperopt)
-        // Scaled value: 0.0005-0.002 (50-200 basis points = 0.05-0.2%)
-        // This makes hold penalty comparable to transaction costs (0.05-0.15%), not 30x weaker
-        let hold_penalty_scale = Decimal::try_from(1000.0)
-            .unwrap_or(Decimal::ONE);
-        let hold_penalty_pct = self.config.hold_penalty_weight / hold_penalty_scale;
+        // Hold penalty weight used directly (0.01-2.0 range from hyperopt).
+        // Previously divided by 1000, making it 0.00001 — negligible vs tx costs (0.05-0.15%).
+        let hold_penalty_pct = self.config.hold_penalty_weight;
         
         // Compare volatility to movement threshold
         let hold_reward = if volatility < self.config.movement_threshold {