Skip to content

Add warning to academy docs #4226

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions docs/Learning-Environment-Design.md
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,14 @@ training a maze-solving agent, you would probably want to change the maze itself
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
Expand Down