MO-Mountaincar

Action Space	Discrete(3)
Observation Shape	(2,)
Observation High	[0.6 0.07]
Observation Low	[-1.2 -0.07]
Reward Shape	(3,)
Reward High	[-1. 0. 0.]
Reward Low	[-1. -1. -1.]
Import	mo_gymnasium.make("mo-mountaincar-v0")

A multi-objective version of the MountainCar environment, where the goal is to reach the top of the mountain.

See Gymnasium’s env for more information.

Reward space:

By default, the reward space is a 3D vector containing the time penalty, and penalties for reversing and going forward.

• time penalty: -1.0 for each time step

• reverse penalty: -1.0 for each time step the action is 0 (reverse)

• forward penalty: -1.0 for each time step the action is 2 (forward)

#Alternatively, the reward can be changed with the following options:

• add_speed_objective: Add an extra objective corresponding to the speed of the car.

• remove_move_penalty: Remove the reverse and forward objectives.

• merge_move_penalty: Merge reverse and forward penalties into a single penalty.