You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Sections the track into three reward zones. The farther the car strays from the centerline, the less it’s rewarded.
defreward_function(params):
# Example of rewarding the agent to follow the centerline# Read input parameterstrack_width=params['track_width']
distance_from_center=params['distance_from_center']
# Calculate 3 markers that are at varying distances away from the centerlinemarker_1=0.1*track_widthmarker_2=0.25*track_widthmarker_3=0.5*track_width# Give higher reward if the car is closer to the centerline and vice versaifdistance_from_center<=marker_1:
reward=1.0elifdistance_from_center<=marker_2:
reward=0.5elifdistance_from_center<=marker_3:
reward=0.1else:
reward=1e-3# likely crashed/close to off trackreturnfloat(reward)