ml-agents/docs/Learning-Environment-Design-Academy.md

Creating an Academy

An Academy orchestrates all the Agent objects in a Unity scene. Every scene containing Agents must contain a single Academy. To use an Academy, you must create your own subclass. However, all the methods you can override are optional.

Use the Academy methods to:

• Initialize the environment after the scene loads
• Reset the environment
• Change things in the environment at each simulation step

See Reinforcement Learning in Unity for a description of the timing of these method calls during a simulation.

Initializing an Academy

Initialization is performed once in an Academy object's life cycle. Use the InitializeAcademy() method for any logic you would normally perform in the standard Unity Start() or Awake() methods.

Note: Because the base Academy implements a Awake() function, you must not implement your own. Because of the way the Unity MonoBehaviour class is defined, implementing your own Awake() function hides the base class version and Unity will call yours instead. Likewise, do not implement a FixedUpdate() function in your Academy subclass.

Resetting an Environment

Implement an AcademyReset() function to alter the environment at the start of each episode. For example, you might want to reset an Agent to its starting position or move a goal to a random position. An environment resets when the reset() method is called on the Python UnityEnvironment.

When you reset an environment, consider the factors that should change so that training is generalizable to different conditions. For example, if you were 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.

Controlling an Environment

The AcademyStep() function is called at every step in the simulation before any Agents are updated. Use this function to update objects in the environment at every step or during the episode between environment resets. For example, if you want to add elements to the environment at random intervals, you can put the logic for creating them in the AcademyStep() function.