[Documentation] Adding a few lines to mention that ML-Agents only works with NN generated with our trainers (#3426)

* [Documentation] Adding a few lines to mention that ML-Agents only works with NN generated with our trainers

* Editing the Limitations doc to reflect the comments;

docs/Limitations.md

 `Academy.Instance.DisableAutomaticStepping()`, and then calling
 `Academy.Instance.EnvironmentStep()`
 
+### Unity Inference Engine Models
+Currently, only models created with our trainers are supported for running
+ML-Agents with a neural network behavior.
+
 ## Python API
 
 ### Python version

docs/Unity-Inference-Engine.md

 [compute shaders](https://docs.unity3d.com/Manual/class-ComputeShader.html)
 to run the neural network within Unity.
 
+__Note__: The ML-Agents toolkit only supports the models created with our
+trainers.
+
 ## Supported devices
 
 Scripting Backends : The Unity Inference Engine is generally faster with