diff --git a/crates/ml/examples/train_baseline_rl.rs b/crates/ml/examples/train_baseline_rl.rs
index 9a3d683de..9a691febd 100644
--- a/crates/ml/examples/train_baseline_rl.rs
+++ b/crates/ml/examples/train_baseline_rl.rs
@@ -387,6 +387,15 @@ fn train_dqn_fold(
         use_qr_dqn: hp_bool(hp, "use_qr_dqn").unwrap_or(false),
         num_quantiles: hp_usize(hp, "num_quantiles").unwrap_or(64),
         noisy_epsilon_floor: hp_f64(hp, "noisy_epsilon_floor").unwrap_or(0.05).into(),
+        // Reward-shaping & environment params — critical for trade generation
+        hold_penalty_weight: hp_f64(hp, "hold_penalty_weight").unwrap_or(0.01),
+        max_position_absolute: hp_f64(hp, "max_position_absolute").unwrap_or(2.0),
+        huber_delta: hp_f64(hp, "huber_delta").unwrap_or(10.0),
+        entropy_coefficient: hp_f64(hp, "entropy_coefficient").map(Some).unwrap_or(Some(0.01)),
+        curiosity_weight: hp_f64(hp, "curiosity_weight").unwrap_or(0.1),
+        weight_decay: hp_f64(hp, "weight_decay").unwrap_or(1e-4),
+        kelly_fractional: hp_f64(hp, "kelly_fractional").unwrap_or(0.5),
+        kelly_max_fraction: hp_f64(hp, "kelly_max_fraction").unwrap_or(0.25),
         ..DQNHyperparameters::default()
     };