MO-Lunar-Lander-Continuous¶
Action Space |
Box(-1.0, 1.0, (2,), float32) |
Observation Shape |
(8,) |
Observation High |
[ 2.5 2.5 10. 10. 6.28 10. 1. 1. ] |
Observation Low |
[ -2.5 -2.5 -10. -10. -6.28 -10. -0. -0. ] |
Reward Shape |
(4,) |
Reward High |
[100. inf 0. 0.] |
Reward Low |
[-100. -inf -1. -1.] |
Import |
|
Description¶
Multi-objective version of the LunarLander environment.
See Gymnasium’s env for more information.
Reward Space¶
The reward is 4-dimensional:
0: -100 if crash, +100 if lands successfully
1: Shaping reward
2: Fuel cost (main engine)
3: Fuel cost (side engine)