reward.py

# assign zeros to paths and 200 to goal-reaching point
for point in points_list:
    print(point)
    if point[1] == goal:
        R[point] = 200
    else:
        R[point] = 0

    if point[0] == goal:
        R[point[::-1]] = 200
    else:
        # reverse of point
        R[point[::-1]]= 0

# add goal point round trip
R[goal,goal]= 200