Using the ML-Agents Toolkit – a basic example

Now that the everything is installed, we can start using the ML-Agents Toolkit. First, let's explain the three main entities in the toolkit:

• The Agent: Obviously, the agent is the central object in the ML-Agents Toolkit. An agent is an object that performs an action, receives information from the environment, and can receive rewards for actions.
• The Brain object: The Brain object is responsible for choosing the agent's actions. At the moment, there are four different Brain types:
  • Player mode: The agent executes actions decided by player input.
  • Heuristic mode: The agent executes actions decided by some hard-coded decision-making system (for example, a Behavior Tree).
  • External mode: The agent executes actions decided by TensorFlow. The brain will communicate with it using the Python API interface.
  • Internal mode...