diff --git a/docs/Installation-Windows.md b/docs/Installation-Windows.md
index 148575c913..6d28058db1 100644
--- a/docs/Installation-Windows.md
+++ b/docs/Installation-Windows.md
@@ -166,10 +166,10 @@ Make sure to replace the relevant directory location with the one you have insta
 </p>
 
 ### Install TensorFlow GPU
-Next, install `tensorflow-gpu` using `pip`. In an Anaconda Prompt with the Conda environment ml-agents activated, type in the following command _(make sure you are connected to the internet)_:
+Next, install `tensorflow-gpu` using `pip`. You'll need version 1.4.0 as newer versions require CUDA 9 which is not yet supported. In an Anaconda Prompt with the Conda environment ml-agents activated, type in the following command _(make sure you are connected to the internet)_:
 
 ```
-pip install tensorflow-gpu
+pip install tensorflow-gpu==1.4.0
 ```
 
 Lastly, you should test to see if everything installed properly and that TensorFlow can identify your GPU. In the same Anaconda Prompt, type in the following command:
diff --git a/docs/Learning-Environment-Examples.md b/docs/Learning-Environment-Examples.md
index 8d0b6187e6..ecb55318eb 100644
--- a/docs/Learning-Environment-Examples.md
+++ b/docs/Learning-Environment-Examples.md
@@ -109,7 +109,7 @@ If you would like to contribute environments, please see our
     * -0.0005 for every step.
     * +1.0 if the agent touches the goal.
     * -1.0 if the agent falls off the platform.
-* Brains: One brain with the following observation/action space.
+* Brains: Two brains, each with the following observation/action space.
     * Vector Observation space: (Continuous) 16 variables corresponding to position and velocities of agent, block, and goal, plus the height of the wall.
     * Vector Action space: (Discrete) Size of 74, corresponding to 14 raycasts each detecting 4 possible objects. plus the global position of the agent and whether or not the agent is grounded.
     * Visual Observations: None.