diff --git a/ml/src/trainers/dqn.rs b/ml/src/trainers/dqn.rs
index 551306b2d..5814ac3a4 100644
--- a/ml/src/trainers/dqn.rs
+++ b/ml/src/trainers/dqn.rs
@@ -1262,13 +1262,9 @@ impl DQNTrainer {
                         // WAVE 9-11: Track Q-value range for production monitoring
                         monitor.track_q_value_range(q_value);
 
-                        // WAVE 11 FIX: Update epsilon per training step (not per epoch)
-                        // This ensures epsilon decays properly: epsilon_start * (epsilon_decay ** step)
-                        // With epsilon_decay=0.995, epsilon reaches 0.05 at step ~2,977 (~2.1 epochs)
-                        {
-                            let mut agent = self.agent.write().await;
-                            agent.update_epsilon();
-                        }
+                        // BUG #29 FIX: Epsilon decay moved to per-epoch (see line ~1340)
+                        // Previous per-batch decay caused premature exploration collapse in short hyperopt trials
+                        // With batch_size=72, epsilon hit floor (0.05) after 2.1 epochs, freezing at 2.2% diversity
                     },
                     Err(e) => {
                         // Log error but continue training (some batches may fail due to sampling issues)
@@ -1331,6 +1327,14 @@ impl DQNTrainer {
                 epoch_duration.as_secs_f64()
             );
 
+            // BUG #29 FIX: Update epsilon once per epoch (not per batch)
+            // This ensures consistent exploration across different batch sizes
+            // With epsilon_decay=0.995, after 15 epochs: 0.3 × (0.995^15) = 0.2783 (27.8% exploration)
+            {
+                let mut agent = self.agent.write().await;
+                agent.update_epsilon();
+            }
+
             // WAVE 9-11: Log Q-value range for production monitoring
             if train_step_count > 0 {
                 info!(