diff --git a/ml/src/trainers/dqn.rs b/ml/src/trainers/dqn.rs
index f38a5fbb2..6f60ddc28 100644
--- a/ml/src/trainers/dqn.rs
+++ b/ml/src/trainers/dqn.rs
@@ -1958,51 +1958,56 @@ impl DQNTrainer {
                 self.feature_stats = Some(stats);
                 info!("✅ WAVE 3 FIX #2: Feature normalization enabled for epoch {}+", stats_collection_epochs + 1);
 
-                // BUG #38 FIX: Clear replay buffer and reset target network
-                info!("🔄 BUG #38 FIX: Clearing replay buffer (removing pre-normalized experiences)");
-                self.clear_replay_buffer().await?;
-
-                info!("🔄 BUG #38 FIX: Resetting target network (updating to normalized feature space)");
-                self.reset_target_network().await?;
-                
-                // Adaptive C51 bounds
+                // Adaptive C51 bounds (MOVED BEFORE buffer clear to use pre-normalized experiences)
                 if self.hyperparams.use_distributional {
                     info!("🎯 C51 Adaptive Bounds: Collecting Q-value statistics from Phase 1...");
-                    
+
+                    // Add buffer state logging
+                    let buffer_size = self.agent.read().await.get_replay_buffer_size()?;
+                    info!("  Buffer state: {} experiences (min required: {})",
+                         buffer_size, self.hyperparams.min_replay_size);
+
                     match self.collect_qvalue_statistics().await {
                         Ok(q_stats) => {
                             let old_v_min = self.hyperparams.v_min;
                             let old_v_max = self.hyperparams.v_max;
                             let (new_v_min, new_v_max) = Self::calculate_adaptive_bounds(&q_stats, 0.3);
-                            
+
                             let old_range = old_v_max - old_v_min;
                             let new_range = new_v_max - new_v_min;
                             let q_range = q_stats.max - q_stats.min;
                             let old_coverage = if q_range > 0.0 { (old_range / q_range) * 100.0 } else { 0.0 };
                             let new_coverage = if q_range > 0.0 { (new_range / q_range) * 100.0 } else { 0.0 };
-                            
-                            info!("  Phase 1 Q-range: [{:.2}, {:.2}] (mean: {:.2}, samples: {})", 
+
+                            info!("  Phase 1 Q-range: [{:.2}, {:.2}] (mean: {:.2}, samples: {})",
                                   q_stats.min, q_stats.max, q_stats.mean, q_stats.sample_count);
                             info!("  Old bounds: ({:.2}, {:.2}) → coverage: {:.2}%",
                                   old_v_min, old_v_max, old_coverage);
                             info!("  New bounds: ({:.2}, {:.2}) → coverage: {:.2}%",
                                   new_v_min, new_v_max, new_coverage);
-                            
+
                             self.reinit_categorical_distribution(new_v_min, new_v_max).await?;
-                            
+
                             // Update hyperparams for logging
                             self.hyperparams.v_min = new_v_min;
                             self.hyperparams.v_max = new_v_max;
-                            
+
                             info!("✅ C51 distribution reinitialized successfully");
                         },
                         Err(e) => {
                             warn!("⚠️  Failed to collect Q-stats: {}", e);
-                            warn!("   Continuing with fixed bounds ({:.2}, {:.2})", 
+                            warn!("   Continuing with fixed bounds ({:.2}, {:.2})",
                                   self.hyperparams.v_min, self.hyperparams.v_max);
                         }
                     }
                 }
+
+                // BUG #38 FIX: Clear replay buffer and reset target network (AFTER C51 stats collection)
+                info!("🔄 BUG #38 FIX: Clearing replay buffer (removing pre-normalized experiences)");
+                self.clear_replay_buffer().await?;
+
+                info!("🔄 BUG #38 FIX: Resetting target network (updating to normalized feature space)");
+                self.reset_target_network().await?;
             } else if epoch < 10 && epoch % 2 == 0 {
                 // Log progress during stats collection phase
                 info!("📊 WAVE 3 FIX #2: Collecting feature statistics (epoch {}/10)", epoch + 1);
diff --git a/ml/trained_models/dqn_epoch_17.safetensors b/ml/trained_models/dqn_epoch_17.safetensors
new file mode 100644
index 000000000..714dcd408
Binary files /dev/null and b/ml/trained_models/dqn_epoch_17.safetensors differ
diff --git a/ml/trained_models/dqn_epoch_8.safetensors b/ml/trained_models/dqn_epoch_8.safetensors
index fe9d7b28b..714dcd408 100644
Binary files a/ml/trained_models/dqn_epoch_8.safetensors and b/ml/trained_models/dqn_epoch_8.safetensors differ
diff --git a/ml/trained_models/dqn_final_epoch15.safetensors b/ml/trained_models/dqn_final_epoch15.safetensors
new file mode 100644
index 000000000..714dcd408
Binary files /dev/null and b/ml/trained_models/dqn_final_epoch15.safetensors differ