diff --git a/crates/ml/src/trainers/dqn/config.rs b/crates/ml/src/trainers/dqn/config.rs
index 44945f209..9c4130eb1 100644
--- a/crates/ml/src/trainers/dqn/config.rs
+++ b/crates/ml/src/trainers/dqn/config.rs
@@ -1262,7 +1262,7 @@ impl DQNHyperparameters {
             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)
-            gradient_clip_norm: Some(10.0), // REVERTED: Back to 10.0 default (production standard)
+            gradient_clip_norm: Some(1.0), // Tight clip — prevents grad explosion with complex reward
             hold_penalty_weight: 0.01,      // Default: 1% penalty weight
             movement_threshold: 0.02,       // Default: 2% price movement threshold
             enable_preprocessing: true,     // Default: preprocessing enabled (Wave 14 Agent 32)