deep-racer.py

def reward_function(params):
    # Read input parameters
    all_wheels_on_track = params['all_wheels_on_track']
    distance_from_center = params['distance_from_center']
    track_width = params['track_width']
    progress = params['progress']
    waypoints = params['waypoints']
    closest_waypoints = params['closest_waypoints']

    # Give a very low reward by default
    reward = 1e-3

    if all_wheels_on_track:
        # Reward for making progress around the track
        reward = progress

        # Calculate the direction to the next waypoint
        next_waypoint = waypoints[closest_waypoints[1]]
        prev_waypoint = waypoints[closest_waypoints[0]]
        track_direction = math.atan2(next_waypoint[1] - prev_waypoint[1], next_waypoint[0] - prev_waypoint[0])

        # Calculate the direction of the car
        direction = params['heading']

        # Calculate the angle between the track direction and the car direction
        direction_diff = abs(track_direction - direction)

        # Penalize for deviating from the shortest route
        if direction_diff > math.pi / 2:
            reward *= 0.8

        # Reward for staying near the center line
        reward -= distance_from_center / (track_width / 2)

        # Adjust speed based on the track geometry
        speed = params['speed']
        straight_ahead = abs(direction_diff) < math.pi / 4
        if straight_ahead:
            # Speed up in straight sections
            reward += 0.2 * (speed / 5.0)
        else:
            # Slow down before corners
            reward -= 0.2 * (speed / 5.0)

    return reward