submission_5_11.py

## Trained with OG DeepRacer car using Shanghai Sudu Training Track
## Top Evaluation on AWS Summit Raceway
##	00:00:35.457	100%	Lap complete
##	00:00:37.045	100%	Lap complete

import math 

def reward_function(params):
    '''
    Example of rewarding the agent to stay inside the two borders of the track
    '''
    
    # Read input parameters
    all_wheels_on_track = params['all_wheels_on_track']
    distance_from_center = params['distance_from_center']
    track_width = params['track_width']
    
    steering = abs(params['steering_angle'])
    direction_stearing=params['steering_angle']
    speed = params['speed']
    
    waypoints = params['waypoints']
    closest_waypoints = params['closest_waypoints']
    heading = params['heading']
    
    # Give a very low reward by default
    reward = 1e-8

    # Give a high reward if no wheels go off the track and
    # the agent is somewhere in between the track borders
    if all_wheels_on_track and (0.5*track_width - distance_from_center) >= 0.05:
        reward = 1.0
    if all_wheels_on_track:
        reward *= 1e-8
        
    next_point = waypoints[closest_waypoints[1]]
    prev_point = waypoints[closest_waypoints[0]]
    track_direction = math.atan2(next_point[1] - prev_point[1], next_point[0] - prev_point[0])
    track_direction = math.degrees(track_direction)
    
    # Penalize the reward if the difference is too large
    direction_diff = abs(track_direction - heading)
    DIRECTION_THRESHOLD = 5.0
    
    malus=1
    
    if direction_diff > DIRECTION_THRESHOLD:
        malus=1-(direction_diff/50)
        if malus<0 or malus>1:
            malus = 0
        reward *= malus
    

    # Always return a float value
    return float(reward)