diff --git a/crates/ml/tests/dqn_training_pipeline_test.rs b/crates/ml/tests/dqn_training_pipeline_test.rs
index 9c885bbac..ab84fcc19 100644
--- a/crates/ml/tests/dqn_training_pipeline_test.rs
+++ b/crates/ml/tests/dqn_training_pipeline_test.rs
@@ -159,15 +159,15 @@ async fn test_dqn_trains_on_es_fut() -> Result<()> {
 
     let checkpoint_dir = create_checkpoint_dir()?;
 
-    // Configure hyperparameters for fast test (10 epochs)
+    // Configure hyperparameters for fast test (5 epochs)
     let mut hyperparams = DQNHyperparameters::conservative();
-    hyperparams.epochs = 10; // Fast test
+    hyperparams.epochs = 5; // Fast CI test
     hyperparams.batch_size = 64;
     hyperparams.learning_rate = 0.001;
     hyperparams.epsilon_start = 0.5; // Reduced for faster training
     hyperparams.epsilon_end = 0.05;
     hyperparams.checkpoint_frequency = 5;
-    hyperparams.early_stopping_enabled = false; // Test all 10 epochs
+    hyperparams.early_stopping_enabled = false; // Test all epochs
 
     println!("   ✅ Configuration ready");
     println!("   📂 Data directory: {}", data_dir);
@@ -295,9 +295,9 @@ async fn test_dqn_loss_decreases() -> Result<()> {
 
     let checkpoint_dir = create_checkpoint_dir()?;
 
-    // Train for 20 epochs to measure convergence
+    // Train for 10 epochs to measure convergence
     let mut hyperparams = DQNHyperparameters::conservative();
-    hyperparams.epochs = 20;
+    hyperparams.epochs = 10;
     hyperparams.batch_size = 64;
     hyperparams.learning_rate = 0.001;
     hyperparams.early_stopping_enabled = false;
@@ -496,7 +496,7 @@ async fn test_dqn_epsilon_greedy() -> Result<()> {
 
     // Configure with high epsilon decay
     let mut hyperparams = DQNHyperparameters::conservative();
-    hyperparams.epochs = 10;
+    hyperparams.epochs = 5;
     hyperparams.epsilon_start = 1.0;
     hyperparams.epsilon_end = 0.01;
     hyperparams.epsilon_decay = 0.9; // Fast decay
@@ -514,14 +514,16 @@ async fn test_dqn_epsilon_greedy() -> Result<()> {
         .await?;
 
     // BUG #40 VERIFIED: With noisy nets enabled (conservative() default),
-    // epsilon must be 0.0 — exploration comes from network noise, not random actions.
+    // epsilon is fixed at noisy_epsilon_floor (0.05) — not decayed, not 1.0.
     // Before the fix, epsilon stayed at 1.0 (100% random actions throughout training).
+    // The noisy_epsilon_floor provides a minimum exploration rate to prevent action collapse
+    // while NoisyNets provide the primary learned exploration signal.
     let final_epsilon = trainer.get_agent_epsilon().await;
     println!("   Final epsilon: {:.4}", final_epsilon);
 
     assert!(
-        final_epsilon < 0.01,
-        "BUG #40: Epsilon should be ~0.0 with noisy nets (got {:.4}). \
+        final_epsilon < 0.10,
+        "BUG #40: Epsilon should be at noisy_epsilon_floor (~0.05) with noisy nets (got {:.4}). \
          If this fails, noisy net epsilon override is broken.",
         final_epsilon
     );
@@ -535,7 +537,7 @@ async fn test_dqn_epsilon_greedy() -> Result<()> {
     );
 
     println!("   Avg Q-value:  {:.4}", avg_q);
-    println!("   ✅ Noisy nets exploration validated (epsilon=0, Q-values drive actions)");
+    println!("   ✅ Noisy nets exploration validated (epsilon=floor, Q-values+noise drive actions)");
 
     Ok(())
 }
diff --git a/crates/ml/tests/dqn_training_smoke_test.rs b/crates/ml/tests/dqn_training_smoke_test.rs
index 193f97d3c..ecf0147f6 100644
--- a/crates/ml/tests/dqn_training_smoke_test.rs
+++ b/crates/ml/tests/dqn_training_smoke_test.rs
@@ -228,11 +228,13 @@ async fn test_dqn_training_smoke() -> Result<()> {
     );
 
     // === ASSERT 6: Epsilon correct for noisy nets (BUG #40 FIX) ===
-    // conservative() enables noisy nets → epsilon must be 0.0 (noise provides exploration)
+    // conservative() enables noisy nets → epsilon fixed at noisy_epsilon_floor (0.05).
+    // NoisyNets provide learned exploration; the floor prevents action collapse.
+    // Before the fix, epsilon stayed at 1.0 (100% random actions throughout training).
     let final_epsilon = trainer.get_agent_epsilon().await;
     assert!(
-        final_epsilon < 0.01,
-        "ASSERT 6 FAILED: Epsilon should be ~0.0 with noisy nets (got {:.4}). BUG #40 fix missing.",
+        final_epsilon < 0.10,
+        "ASSERT 6 FAILED: Epsilon should be at noisy_epsilon_floor (~0.05) with noisy nets (got {:.4}). BUG #40 fix missing.",
         final_epsilon
     );