diff --git a/18_reinforcement_learning.ipynb b/18_reinforcement_learning.ipynb
index 1db21d5..7f2b685 100644
--- a/18_reinforcement_learning.ipynb
+++ b/18_reinforcement_learning.ipynb
@@ -1376,7 +1376,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Lastly, let's create a function that will sample some experiences from the replay memory and perform a training step:"
+    "Lastly, let's create a function that will sample some experiences from the replay memory and perform a training step:\n",
+    "\n",
+    "**Note**: the first 3 releases of the 2nd edition were missing the `reshape()` operation which converts `target_Q_values` to a column vector (this is required by the `loss_fn()`)."
    ]
   },
   {