question on pendulum reward function

[Haichao-Zhang]

Can you explain why this reward function (-cos(theta)-0.1*sin(theta) ... ) is used for pendulum?

POPLIN/dmbrl/config/gym_pendulum.py

Line 104 in edd8dba

costs = y + .1 * x + .1 * (thetadot ** 2) + .001 * (torque ** 2)

And why does it need to be different from the original reward function from openai-gym?