Hands-On Neuroevolution with Python

Maze simulation environment implementation

To simulate the solver agent navigating the maze, we need to define an environment that manages the configuration of the maze, tracks the position of the maze-solving agent, and provides inputs to the sensor data arrays of the navigating robot.

All of these features fit into one logical block that is encapsulated into the MazeEnvironment Python class, which has the following fields (as can be seen from the class constructor):

    def __init__(self, agent, walls, exit_point, exit_range=5.0):        self.walls = walls        self.exit_point = exit_point        self.exit_range = exit_range        # The maze navigating agent        self.agent = agent        # The flag to indicate if exit was found        self.exit_found = False # The initial distance ...