diff --git a/crates/ml/src/ppo/continuous_policy.rs b/crates/ml/src/ppo/continuous_policy.rs
index 84e8f586b..909b64eea 100644
--- a/crates/ml/src/ppo/continuous_policy.rs
+++ b/crates/ml/src/ppo/continuous_policy.rs
@@ -330,7 +330,7 @@ impl ContinuousPolicyNetwork {
 
         let log_prob = (log_2pi_tensor * (-0.5))?
             .sub(&log_stds)?
-            .sub(&(squared_diff * (-0.5))?)?;
+            .sub(&(squared_diff * 0.5)?)?;
 
         Ok(log_prob.squeeze(1)?) // Remove extra dimension if present
     }
@@ -567,9 +567,8 @@ mod tests {
         // Action should be in bounds
         assert!(action >= 0.0 && action <= 1.0);
 
-        // Log prob should be finite and negative
+        // Log prob should be finite (can be positive for continuous distributions with small σ)
         assert!(log_prob.is_finite());
-        assert!(log_prob <= 0.0);
     }
 
     #[test]
@@ -592,7 +591,7 @@ mod tests {
         assert_eq!(log_probs.dims(), &[2]);
 
         let log_probs_vec = log_probs.to_vec1::<f32>().unwrap();
-        assert!(log_probs_vec.iter().all(|&lp| lp.is_finite() && lp <= 0.0));
+        assert!(log_probs_vec.iter().all(|&lp| lp.is_finite()));
     }
 
     #[test]