reward_function.py

# Encourage lander to use as little fuel as possible
# i.e. 0.85, or 0.32
fuel_conservation = fuel_remaining / total_fuel 

if distance_to_goal is decreasing:
   if speed < threshold:
       if position is on landing pad:
           # Land successfully; give a big reward
           landing_reward = 100
           # Multiply percentage of remaining fuel
           reward = landing_reward * fuel_conservation
       else:
           # Landing outside of landing pad
           reward = -10
   else:
       # Crashed
       reward = -100
else:
   # Encourage agents to approach the surface instead of
   # hanging in the air
   distance_reward = 1 - (distance_to_goal / distance_max)**0.5
   reward = distance_reward * fuel_conservation