Update docs/Learning-Environment-Design.md

Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>

docs/Learning-Environment-Design.md

 for each training episode. Otherwise, the agent would probably on learn to solve
 one, particular maze, not mazes in general.
 
+#### Academy Pitfalls
+
+In some games, it may be desirable to step the environment with the Academy manually via `Academy.Instance.EnvironmentStep()`.
+Note, stepping manually is an advanced scenario and some care is required.
+If this is the case, be sure `Academy.Instance.EnvironmentStep()` is not called directly or indirectly by the agent's
+API e.g. from the `CollectObservations()`, `OnActionReceived`, and `Heuristic()` functions as this will
+cause an infinite loop that prevents the main Unity `Update()` function from being called.
+
 ### Multiple Areas
 
 In many of the example environments, many copies of the training area are