MO-Hopper¶
Action Space |
Box(-1.0, 1.0, (3,), float32) |
Observation Shape |
(11,) |
Observation High |
inf |
Observation Low |
-inf |
Reward Shape |
(3,) |
Reward High |
[inf inf inf] |
Reward Low |
[-inf -inf -inf] |
Import |
|
Description¶
Multi-objective version of the HopperEnv environment.
See Gymnasium’s env for more information.
The original Gymnasium’s ‘Hopper-v5’ is recovered by the following linear scalarization:
env = mo_gym.make(‘mo-hopper-v5’) LinearReward(env, weight=np.array([1.0, 0.0, 1e-3]))
Reward Space¶
The reward is 3-dimensional:
0: Reward for going forward on the x-axis
1: Reward for jumping high on the z-axis
2: Control cost of the action If the cost_objective flag is set to False, the reward is 2-dimensional, and the cost is added to other objectives.
A 2-objective version (without the cost objective as a separate objective) can be instantiated via: env = mo_gym.make(‘mo-hopper-2obj-v5’)
Version History¶
v5: The 2-objective version has now id ‘mo-hopper-2obj-v5’, instead of ‘mo-hopper-2d-v4’. See https://gymnasium.farama.org/environments/mujoco/hopper/#version-history